Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

loss nan #6

Closed
bei-startdt opened this issue Apr 16, 2019 · 16 comments
Closed

loss nan #6

bei-startdt opened this issue Apr 16, 2019 · 16 comments

Comments

@bei-startdt
Copy link

I try to train coco, but loss is nan.
this is my training script:

CUDA_VISIBLE_DEVICES=1,3,4,5 python -m torch.distributed.launch \
    --nproc_per_node=4 \
    --master_port=$((RANDOM + 10000)) \
    tools/train_net.py \
    --skip-test \
    --config-file configs/fcos/fcos_R_50_FPN_1x.yaml \
    DATALOADER.NUM_WORKERS 2 \
    OUTPUT_DIR training_dir/fcos_R_50_FPN_1x

this is my result

2019-04-16 09:19:17,383 maskrcnn_benchmark.trainer INFO: Start training
2019-04-16 09:19:33,719 maskrcnn_benchmark.trainer INFO: eta: 20:24:50  iter: 20  loss: 4.2079 (4.8923)  loss_centerness: 0.6670 (0.6685)  loss_cls: 0.9797 (0.9730)  loss_reg: 2.5527 (3.2508)  time: 0.6882 (0.8167)  data: 0.0219 (0.0651)  lr: 0.003333  max mem: 7051
2019-04-16 09:19:48,380 maskrcnn_benchmark.trainer INFO: eta: 19:21:49  iter: 40  loss: 3.2185 (4.0965)  loss_centerness: 0.6607 (0.6652)  loss_cls: 0.8450 (0.9074)  loss_reg: 1.6475 (2.5240)  time: 0.6947 (0.7749)  data: 0.0265 (0.0462)  lr: 0.003333  max mem: 7051
2019-04-16 09:20:02,270 maskrcnn_benchmark.trainer INFO: eta: 18:41:23  iter: 60  loss: 2.9554 (3.7219)  loss_centerness: 0.6592 (0.6634)  loss_cls: 0.7685 (0.8647)  loss_reg: 1.5265 (2.1938)  time: 0.6972 (0.7481)  data: 0.0283 (0.0399)  lr: 0.003333  max mem: 7051
2019-04-16 09:20:15,608 maskrcnn_benchmark.trainer INFO: eta: 18:10:43  iter: 80  loss: 2.8321 (nan)  loss_centerness: 0.6582 (nan)  loss_cls: 0.7013 (nan)  loss_reg: 1.4726 (nan)  time: 0.6690 (0.7278)  data: 0.0277 (0.0374)  lr: 0.003333  max mem: 7051
2019-04-16 09:20:28,939 maskrcnn_benchmark.trainer INFO: eta: 17:52:08  iter: 100  loss: nan (nan)  loss_centerness: nan (nan)  loss_cls: nan (nan)  loss_reg: nan (nan)  time: 0.6653 (0.7156)  data: 0.0262 (0.0353)  lr: 0.003333  max mem: 7051

I have tried for 3 times, always nan.
what's wrong with me?
@tianzhi0549
Copy link
Owner

Can you post your full logs here? Maybe we can help you.

@bei-startdt
Copy link
Author 

2019-04-16 09:44:24,883 maskrcnn_benchmark INFO: Using 4 GPUs
2019-04-16 09:44:24,883 maskrcnn_benchmark INFO: Namespace(config_file='configs/fcos/fcos_R_50_FPN_1x.yaml', distributed=True, local_rank=0, opts=['DATALOADER.NUM_WORKERS', '2', 'OUTPUT_DIR', 'training_dir/fcos_R_50_FPN_1x'], skip_test=True)
2019-04-16 09:44:24,883 maskrcnn_benchmark INFO: Collecting env info (might take some time)
2019-04-16 09:44:27,749 maskrcnn_benchmark INFO:
PyTorch version: 1.0.0
Is debug build: No
CUDA used to build PyTorch: 9.0.176

OS: Ubuntu 16.04.6 LTS
GCC version: (Ubuntu 5.4.0-6ubuntu1~16.04.11) 5.4.0 20160609
CMake version: Could not collect

Python version: 3.6
Is CUDA available: Yes
CUDA runtime version: Could not collect
GPU models and configuration:
GPU 0: GeForce GTX 1080 Ti
GPU 1: GeForce GTX 1080 Ti
GPU 2: GeForce GTX 1080 Ti
GPU 3: GeForce GTX 1080 Ti
GPU 4: GeForce GTX 1080 Ti
GPU 5: GeForce GTX 1080 Ti
GPU 6: GeForce GTX 1080 Ti
GPU 7: GeForce GTX 1080 Ti

Nvidia driver version: 415.27
cuDNN version: Could not collect

Versions of relevant libraries:
[pip] Could not collect
[conda] torch                     1.0.0                    pypi_0    pypi
[conda] torchvision               0.2.2.post3              pypi_0    pypi
        Pillow (6.0.0)
2019-04-16 09:44:27,749 maskrcnn_benchmark INFO: Loaded configuration file configs/fcos/fcos_R_50_FPN_1x.yaml
2019-04-16 09:44:27,749 maskrcnn_benchmark INFO:
MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50"
  RPN_ONLY: True
  FCOS_ON: True
  BACKBONE:
    CONV_BODY: "R-50-FPN-RETINANET"
  RESNETS:
    BACKBONE_OUT_CHANNELS: 256
  RETINANET:
    USE_C5: False # FCOS uses P5 instead of C5
DATASETS:
  TRAIN: ("coco_2014_train", "coco_2014_valminusminival")
  TEST: ("coco_2014_minival",)
INPUT:
  MIN_SIZE_TRAIN: (800,)
  MAX_SIZE_TRAIN: 1333
  MIN_SIZE_TEST: 800
  MAX_SIZE_TEST: 1333
DATALOADER:
  SIZE_DIVISIBILITY: 32
SOLVER:
  BASE_LR: 0.01
  WEIGHT_DECAY: 0.0001
  STEPS: (60000, 80000)
  MAX_ITER: 90000
  IMS_PER_BATCH: 16
  WARMUP_METHOD: "constant"

2019-04-16 09:44:27,750 maskrcnn_benchmark INFO: Running with config:
DATALOADER:
  ASPECT_RATIO_GROUPING: True
  NUM_WORKERS: 2
  SIZE_DIVISIBILITY: 32
DATASETS:
  TEST: ('coco_2014_minival',)
  TRAIN: ('coco_2014_train', 'coco_2014_valminusminival')
INPUT:
  MAX_SIZE_TEST: 1333
  MAX_SIZE_TRAIN: 1333
  MIN_SIZE_RANGE_TRAIN: (-1, -1)
  MIN_SIZE_TEST: 800
  MIN_SIZE_TRAIN: (800,)
  PIXEL_MEAN: [102.9801, 115.9465, 122.7717]
  PIXEL_STD: [1.0, 1.0, 1.0]
  TO_BGR255: True
MODEL:
  BACKBONE:
    CONV_BODY: R-50-FPN-RETINANET
    FREEZE_CONV_BODY_AT: 2
    USE_GN: False
  CLS_AGNOSTIC_BBOX_REG: False
  DEVICE: cuda
  FBNET:
    ARCH: default
    ARCH_DEF:
    BN_TYPE: bn
    DET_HEAD_BLOCKS: []
    DET_HEAD_LAST_SCALE: 1.0
    DET_HEAD_STRIDE: 0
    DW_CONV_SKIP_BN: True
    DW_CONV_SKIP_RELU: True
    KPTS_HEAD_BLOCKS: []
    KPTS_HEAD_LAST_SCALE: 0.0
    KPTS_HEAD_STRIDE: 0
    MASK_HEAD_BLOCKS: []
    MASK_HEAD_LAST_SCALE: 0.0
    MASK_HEAD_STRIDE: 0
    RPN_BN_TYPE:
    RPN_HEAD_BLOCKS: 0
    SCALE_FACTOR: 1.0
    WIDTH_DIVISOR: 1
  FCOS:
    FPN_STRIDES: [8, 16, 32, 64, 128]
    INFERENCE_TH: 0.05
    LOSS_ALPHA: 0.25
    LOSS_GAMMA: 2.0
    NMS_TH: 0.4
    NUM_CLASSES: 81
    NUM_CONVS: 4
    PRE_NMS_TOP_N: 1000
    PRIOR_PROB: 0.01
  FCOS_ON: True
  FPN:
    USE_GN: False
    USE_RELU: False
  GROUP_NORM:
    DIM_PER_GP: -1
    EPSILON: 1e-05
    NUM_GROUPS: 32
  KEYPOINT_ON: False
  MASK_ON: False
  META_ARCHITECTURE: GeneralizedRCNN
  RESNETS:
    BACKBONE_OUT_CHANNELS: 256
    NUM_GROUPS: 1
    RES2_OUT_CHANNELS: 256
    RES5_DILATION: 1
    STEM_FUNC: StemWithFixedBatchNorm
    STEM_OUT_CHANNELS: 64
    STRIDE_IN_1X1: True
    TRANS_FUNC: BottleneckWithFixedBatchNorm
    WIDTH_PER_GROUP: 64
  RETINANET:
    ANCHOR_SIZES: (32, 64, 128, 256, 512)
    ANCHOR_STRIDES: (8, 16, 32, 64, 128)
    ASPECT_RATIOS: (0.5, 1.0, 2.0)
    BBOX_REG_BETA: 0.11
    BBOX_REG_WEIGHT: 4.0
    BG_IOU_THRESHOLD: 0.4
    FG_IOU_THRESHOLD: 0.5
    INFERENCE_TH: 0.05
    LOSS_ALPHA: 0.25
    LOSS_GAMMA: 2.0
    NMS_TH: 0.4
    NUM_CLASSES: 81
    NUM_CONVS: 4
    OCTAVE: 2.0
    PRE_NMS_TOP_N: 1000
    PRIOR_PROB: 0.01
    SCALES_PER_OCTAVE: 3
    STRADDLE_THRESH: 0
    USE_C5: False
  RETINANET_ON: False
  ROI_BOX_HEAD:
    CONV_HEAD_DIM: 256
    DILATION: 1
    FEATURE_EXTRACTOR: ResNet50Conv5ROIFeatureExtractor
    MLP_HEAD_DIM: 1024
    NUM_CLASSES: 81
    NUM_STACKED_CONVS: 4
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_SCALES: (0.0625,)
    PREDICTOR: FastRCNNPredictor
    USE_GN: False
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 512
    BBOX_REG_WEIGHTS: (10.0, 10.0, 5.0, 5.0)
    BG_IOU_THRESHOLD: 0.5
    DETECTIONS_PER_IMG: 100
    FG_IOU_THRESHOLD: 0.5
    NMS: 0.5
    POSITIVE_FRACTION: 0.25
    SCORE_THRESH: 0.05
    USE_FPN: False
  ROI_KEYPOINT_HEAD:
    CONV_LAYERS: (512, 512, 512, 512, 512, 512, 512, 512)
    FEATURE_EXTRACTOR: KeypointRCNNFeatureExtractor
    MLP_HEAD_DIM: 1024
    NUM_CLASSES: 17
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_SCALES: (0.0625,)
    PREDICTOR: KeypointRCNNPredictor
    RESOLUTION: 14
    SHARE_BOX_FEATURE_EXTRACTOR: True
  ROI_MASK_HEAD:
    CONV_LAYERS: (256, 256, 256, 256)
    DILATION: 1
    FEATURE_EXTRACTOR: ResNet50Conv5ROIFeatureExtractor
    MLP_HEAD_DIM: 1024
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_SCALES: (0.0625,)
    POSTPROCESS_MASKS: False
    POSTPROCESS_MASKS_THRESHOLD: 0.5
    PREDICTOR: MaskRCNNC4Predictor
    RESOLUTION: 14
    SHARE_BOX_FEATURE_EXTRACTOR: True
    USE_GN: False
  RPN:
    ANCHOR_SIZES: (32, 64, 128, 256, 512)
    ANCHOR_STRIDE: (16,)
    ASPECT_RATIOS: (0.5, 1.0, 2.0)
    BATCH_SIZE_PER_IMAGE: 256
    BG_IOU_THRESHOLD: 0.3
    FG_IOU_THRESHOLD: 0.7
    FPN_POST_NMS_TOP_N_TEST: 2000
    FPN_POST_NMS_TOP_N_TRAIN: 2000
    MIN_SIZE: 0
    NMS_THRESH: 0.7
    POSITIVE_FRACTION: 0.5
    POST_NMS_TOP_N_TEST: 1000
    POST_NMS_TOP_N_TRAIN: 2000
    PRE_NMS_TOP_N_TEST: 6000
    PRE_NMS_TOP_N_TRAIN: 12000
    RPN_HEAD: SingleConvRPNHead
    STRADDLE_THRESH: 0
    USE_FPN: False
  RPN_ONLY: True
  WEIGHT: catalog://ImageNetPretrained/MSRA/R-50
OUTPUT_DIR: training_dir/fcos_R_50_FPN_1x
PATHS_CATALOG: /data/bei/FCOS/maskrcnn_benchmark/config/paths_catalog.py
SOLVER:
  BASE_LR: 0.01
  BIAS_LR_FACTOR: 2
  CHECKPOINT_PERIOD: 2500
  GAMMA: 0.1
  IMS_PER_BATCH: 16
  MAX_ITER: 90000
  MOMENTUM: 0.9
  STEPS: (60000, 80000)
  WARMUP_FACTOR: 0.3333333333333333
  WARMUP_ITERS: 500
  WARMUP_METHOD: constant
  WEIGHT_DECAY: 0.0001
  WEIGHT_DECAY_BIAS: 0
TEST:
  DETECTIONS_PER_IMG: 100
  EXPECTED_RESULTS: []
  EXPECTED_RESULTS_SIGMA_TOL: 4
  IMS_PER_BATCH: 8
2019-04-16 09:44:28,652 maskrcnn_benchmark.utils.checkpoint INFO: Loading checkpoint from catalog://ImageNetPretrained/MSRA/R-50
2019-04-16 09:44:28,652 maskrcnn_benchmark.utils.checkpoint INFO: catalog://ImageNetPretrained/MSRA/R-50 points to https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
2019-04-16 09:44:28,681 maskrcnn_benchmark.utils.checkpoint INFO: url https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl cached in /home/wangjiangben/.torch/models/R-50.pkl
2019-04-16 09:44:28,769 maskrcnn_benchmark.utils.c2_model_loading INFO: Remapping C2 weights
2019-04-16 09:44:28,769 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: conv1_b              mapped name: conv1.bias
2019-04-16 09:44:28,769 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: conv1_w              mapped name: conv1.weight
2019-04-16 09:44:28,769 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: fc1000_b             mapped name: fc1000.bias
2019-04-16 09:44:28,769 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: fc1000_w             mapped name: fc1000.weight
2019-04-16 09:44:28,769 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_b     mapped name: layer1.0.downsample.0.bias
2019-04-16 09:44:28,769 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_bn_b  mapped name: layer1.0.downsample.1.bias
2019-04-16 09:44:28,769 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_bn_s  mapped name: layer1.0.downsample.1.weight
2019-04-16 09:44:28,769 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_w     mapped name: layer1.0.downsample.0.weight
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_b    mapped name: layer1.0.conv1.bias
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_bn_b mapped name: layer1.0.bn1.bias
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_bn_s mapped name: layer1.0.bn1.weight
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_w    mapped name: layer1.0.conv1.weight
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_b    mapped name: layer1.0.conv2.bias
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_bn_b mapped name: layer1.0.bn2.bias
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_bn_s mapped name: layer1.0.bn2.weight
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_w    mapped name: layer1.0.conv2.weight
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_b    mapped name: layer1.0.conv3.bias
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_bn_b mapped name: layer1.0.bn3.bias
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_bn_s mapped name: layer1.0.bn3.weight
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_w    mapped name: layer1.0.conv3.weight
2019-04-16 09:44:28,770 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_b    mapped name: layer1.1.conv1.bias
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_bn_b mapped name: layer1.1.bn1.bias
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_bn_s mapped name: layer1.1.bn1.weight
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_w    mapped name: layer1.1.conv1.weight
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_b    mapped name: layer1.1.conv2.bias
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_bn_b mapped name: layer1.1.bn2.bias
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_bn_s mapped name: layer1.1.bn2.weight
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_w    mapped name: layer1.1.conv2.weight
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_b    mapped name: layer1.1.conv3.bias
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_bn_b mapped name: layer1.1.bn3.bias
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_bn_s mapped name: layer1.1.bn3.weight
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_w    mapped name: layer1.1.conv3.weight
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_b    mapped name: layer1.2.conv1.bias
2019-04-16 09:44:28,771 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_bn_b mapped name: layer1.2.bn1.bias
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_bn_s mapped name: layer1.2.bn1.weight
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_w    mapped name: layer1.2.conv1.weight
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_b    mapped name: layer1.2.conv2.bias
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_bn_b mapped name: layer1.2.bn2.bias
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_bn_s mapped name: layer1.2.bn2.weight
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_w    mapped name: layer1.2.conv2.weight
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_b    mapped name: layer1.2.conv3.bias
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_bn_b mapped name: layer1.2.bn3.bias
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_bn_s mapped name: layer1.2.bn3.weight
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_w    mapped name: layer1.2.conv3.weight
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_b     mapped name: layer2.0.downsample.0.bias
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_bn_b  mapped name: layer2.0.downsample.1.bias
2019-04-16 09:44:28,772 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_bn_s  mapped name: layer2.0.downsample.1.weight
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_w     mapped name: layer2.0.downsample.0.weight
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_b    mapped name: layer2.0.conv1.bias
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_bn_b mapped name: layer2.0.bn1.bias
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_bn_s mapped name: layer2.0.bn1.weight
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_w    mapped name: layer2.0.conv1.weight
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_b    mapped name: layer2.0.conv2.bias
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_bn_b mapped name: layer2.0.bn2.bias
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_bn_s mapped name: layer2.0.bn2.weight
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_w    mapped name: layer2.0.conv2.weight
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_b    mapped name: layer2.0.conv3.bias
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_bn_b mapped name: layer2.0.bn3.bias
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_bn_s mapped name: layer2.0.bn3.weight
2019-04-16 09:44:28,773 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_w    mapped name: layer2.0.conv3.weight
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_b    mapped name: layer2.1.conv1.bias
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_bn_b mapped name: layer2.1.bn1.bias
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_bn_s mapped name: layer2.1.bn1.weight
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_w    mapped name: layer2.1.conv1.weight
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_b    mapped name: layer2.1.conv2.bias
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_bn_b mapped name: layer2.1.bn2.bias
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_bn_s mapped name: layer2.1.bn2.weight
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_w    mapped name: layer2.1.conv2.weight
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_b    mapped name: layer2.1.conv3.bias
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_bn_b mapped name: layer2.1.bn3.bias
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_bn_s mapped name: layer2.1.bn3.weight
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_w    mapped name: layer2.1.conv3.weight
2019-04-16 09:44:28,774 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_b    mapped name: layer2.2.conv1.bias
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_bn_b mapped name: layer2.2.bn1.bias
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_bn_s mapped name: layer2.2.bn1.weight
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_w    mapped name: layer2.2.conv1.weight
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_b    mapped name: layer2.2.conv2.bias
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_bn_b mapped name: layer2.2.bn2.bias
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_bn_s mapped name: layer2.2.bn2.weight
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_w    mapped name: layer2.2.conv2.weight
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_b    mapped name: layer2.2.conv3.bias
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_bn_b mapped name: layer2.2.bn3.bias
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_bn_s mapped name: layer2.2.bn3.weight
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_w    mapped name: layer2.2.conv3.weight
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_b    mapped name: layer2.3.conv1.bias
2019-04-16 09:44:28,775 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_bn_b mapped name: layer2.3.bn1.bias
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_bn_s mapped name: layer2.3.bn1.weight
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_w    mapped name: layer2.3.conv1.weight
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_b    mapped name: layer2.3.conv2.bias
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_bn_b mapped name: layer2.3.bn2.bias
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_bn_s mapped name: layer2.3.bn2.weight
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_w    mapped name: layer2.3.conv2.weight
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_b    mapped name: layer2.3.conv3.bias
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_bn_b mapped name: layer2.3.bn3.bias
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_bn_s mapped name: layer2.3.bn3.weight
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_w    mapped name: layer2.3.conv3.weight
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_b     mapped name: layer3.0.downsample.0.bias
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_bn_b  mapped name: layer3.0.downsample.1.bias
2019-04-16 09:44:28,776 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_bn_s  mapped name: layer3.0.downsample.1.weight
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_w     mapped name: layer3.0.downsample.0.weight
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_b    mapped name: layer3.0.conv1.bias
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_bn_b mapped name: layer3.0.bn1.bias
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_bn_s mapped name: layer3.0.bn1.weight
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_w    mapped name: layer3.0.conv1.weight
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_b    mapped name: layer3.0.conv2.bias
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_bn_b mapped name: layer3.0.bn2.bias
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_bn_s mapped name: layer3.0.bn2.weight
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_w    mapped name: layer3.0.conv2.weight
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_b    mapped name: layer3.0.conv3.bias
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_bn_b mapped name: layer3.0.bn3.bias
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_bn_s mapped name: layer3.0.bn3.weight
2019-04-16 09:44:28,777 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_w    mapped name: layer3.0.conv3.weight
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_b    mapped name: layer3.1.conv1.bias
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_bn_b mapped name: layer3.1.bn1.bias
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_bn_s mapped name: layer3.1.bn1.weight
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_w    mapped name: layer3.1.conv1.weight
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_b    mapped name: layer3.1.conv2.bias
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_bn_b mapped name: layer3.1.bn2.bias
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_bn_s mapped name: layer3.1.bn2.weight
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_w    mapped name: layer3.1.conv2.weight
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_b    mapped name: layer3.1.conv3.bias
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_bn_b mapped name: layer3.1.bn3.bias
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_bn_s mapped name: layer3.1.bn3.weight
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_w    mapped name: layer3.1.conv3.weight
2019-04-16 09:44:28,778 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_b    mapped name: layer3.2.conv1.bias
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_bn_b mapped name: layer3.2.bn1.bias
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_bn_s mapped name: layer3.2.bn1.weight
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_w    mapped name: layer3.2.conv1.weight
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_b    mapped name: layer3.2.conv2.bias
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_bn_b mapped name: layer3.2.bn2.bias
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_bn_s mapped name: layer3.2.bn2.weight
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_w    mapped name: layer3.2.conv2.weight
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_b    mapped name: layer3.2.conv3.bias
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_bn_b mapped name: layer3.2.bn3.bias
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_bn_s mapped name: layer3.2.bn3.weight
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_w    mapped name: layer3.2.conv3.weight
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_b    mapped name: layer3.3.conv1.bias
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_bn_b mapped name: layer3.3.bn1.bias
2019-04-16 09:44:28,779 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_bn_s mapped name: layer3.3.bn1.weight
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_w    mapped name: layer3.3.conv1.weight
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_b    mapped name: layer3.3.conv2.bias
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_bn_b mapped name: layer3.3.bn2.bias
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_bn_s mapped name: layer3.3.bn2.weight
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_w    mapped name: layer3.3.conv2.weight
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_b    mapped name: layer3.3.conv3.bias
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_bn_b mapped name: layer3.3.bn3.bias
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_bn_s mapped name: layer3.3.bn3.weight
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_w    mapped name: layer3.3.conv3.weight
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_b    mapped name: layer3.4.conv1.bias
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_bn_b mapped name: layer3.4.bn1.bias
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_bn_s mapped name: layer3.4.bn1.weight
2019-04-16 09:44:28,780 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_w    mapped name: layer3.4.conv1.weight
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_b    mapped name: layer3.4.conv2.bias
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_bn_b mapped name: layer3.4.bn2.bias
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_bn_s mapped name: layer3.4.bn2.weight
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_w    mapped name: layer3.4.conv2.weight
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_b    mapped name: layer3.4.conv3.bias
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_bn_b mapped name: layer3.4.bn3.bias
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_bn_s mapped name: layer3.4.bn3.weight
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_w    mapped name: layer3.4.conv3.weight
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_b    mapped name: layer3.5.conv1.bias
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_bn_b mapped name: layer3.5.bn1.bias
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_bn_s mapped name: layer3.5.bn1.weight
2019-04-16 09:44:28,781 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_w    mapped name: layer3.5.conv1.weight
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_b    mapped name: layer3.5.conv2.bias
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_bn_b mapped name: layer3.5.bn2.bias
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_bn_s mapped name: layer3.5.bn2.weight
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_w    mapped name: layer3.5.conv2.weight
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_b    mapped name: layer3.5.conv3.bias
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_bn_b mapped name: layer3.5.bn3.bias
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_bn_s mapped name: layer3.5.bn3.weight
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_w    mapped name: layer3.5.conv3.weight
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_b     mapped name: layer4.0.downsample.0.bias
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_bn_b  mapped name: layer4.0.downsample.1.bias
2019-04-16 09:44:28,782 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_bn_s  mapped name: layer4.0.downsample.1.weight
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_w     mapped name: layer4.0.downsample.0.weight
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_b    mapped name: layer4.0.conv1.bias
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_bn_b mapped name: layer4.0.bn1.bias
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_bn_s mapped name: layer4.0.bn1.weight
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_w    mapped name: layer4.0.conv1.weight
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_b    mapped name: layer4.0.conv2.bias
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_bn_b mapped name: layer4.0.bn2.bias
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_bn_s mapped name: layer4.0.bn2.weight
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_w    mapped name: layer4.0.conv2.weight
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_b    mapped name: layer4.0.conv3.bias
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_bn_b mapped name: layer4.0.bn3.bias
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_bn_s mapped name: layer4.0.bn3.weight
2019-04-16 09:44:28,783 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_w    mapped name: layer4.0.conv3.weight
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_b    mapped name: layer4.1.conv1.bias
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_bn_b mapped name: layer4.1.bn1.bias
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_bn_s mapped name: layer4.1.bn1.weight
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_w    mapped name: layer4.1.conv1.weight
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_b    mapped name: layer4.1.conv2.bias
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_bn_b mapped name: layer4.1.bn2.bias
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_bn_s mapped name: layer4.1.bn2.weight
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_w    mapped name: layer4.1.conv2.weight
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_b    mapped name: layer4.1.conv3.bias
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_bn_b mapped name: layer4.1.bn3.bias
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_bn_s mapped name: layer4.1.bn3.weight
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_w    mapped name: layer4.1.conv3.weight
2019-04-16 09:44:28,784 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_b    mapped name: layer4.2.conv1.bias
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_bn_b mapped name: layer4.2.bn1.bias
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_bn_s mapped name: layer4.2.bn1.weight
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_w    mapped name: layer4.2.conv1.weight
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_b    mapped name: layer4.2.conv2.bias
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_bn_b mapped name: layer4.2.bn2.bias
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_bn_s mapped name: layer4.2.bn2.weight
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_w    mapped name: layer4.2.conv2.weight
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_b    mapped name: layer4.2.conv3.bias
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_bn_b mapped name: layer4.2.bn3.bias
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_bn_s mapped name: layer4.2.bn3.weight
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_w    mapped name: layer4.2.conv3.weight
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res_conv1_bn_b       mapped name: bn1.bias
2019-04-16 09:44:28,785 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res_conv1_bn_s       mapped name: bn1.weight
2019-04-16 09:44:28,800 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn1.bias                  loaded from layer1.0.bn1.bias            of shape (64,)
2019-04-16 09:44:28,800 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn1.weight                loaded from layer1.0.bn1.weight          of shape (64,)
2019-04-16 09:44:28,800 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn2.bias                  loaded from layer1.0.bn2.bias            of shape (64,)
2019-04-16 09:44:28,800 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn2.weight                loaded from layer1.0.bn2.weight          of shape (64,)
2019-04-16 09:44:28,800 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn3.bias                  loaded from layer1.0.bn3.bias            of shape (256,)
2019-04-16 09:44:28,800 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn3.weight                loaded from layer1.0.bn3.weight          of shape (256,)
2019-04-16 09:44:28,800 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.conv1.weight              loaded from layer1.0.conv1.weight        of shape (64, 64, 1, 1)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.conv2.weight              loaded from layer1.0.conv2.weight        of shape (64, 64, 3, 3)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.conv3.weight              loaded from layer1.0.conv3.weight        of shape (256, 64, 1, 1)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.downsample.0.weight       loaded from layer1.0.downsample.0.weight of shape (256, 64, 1, 1)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.downsample.1.bias         loaded from layer1.0.downsample.1.bias   of shape (256,)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.downsample.1.weight       loaded from layer1.0.downsample.1.weight of shape (256,)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn1.bias                  loaded from layer1.1.bn1.bias            of shape (64,)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn1.weight                loaded from layer1.1.bn1.weight          of shape (64,)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn2.bias                  loaded from layer1.1.bn2.bias            of shape (64,)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn2.weight                loaded from layer1.1.bn2.weight          of shape (64,)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn3.bias                  loaded from layer1.1.bn3.bias            of shape (256,)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn3.weight                loaded from layer1.1.bn3.weight          of shape (256,)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.conv1.weight              loaded from layer1.1.conv1.weight        of shape (64, 256, 1, 1)
2019-04-16 09:44:28,801 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.conv2.weight              loaded from layer1.1.conv2.weight        of shape (64, 64, 3, 3)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.conv3.weight              loaded from layer1.1.conv3.weight        of shape (256, 64, 1, 1)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn1.bias                  loaded from layer1.2.bn1.bias            of shape (64,)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn1.weight                loaded from layer1.2.bn1.weight          of shape (64,)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn2.bias                  loaded from layer1.2.bn2.bias            of shape (64,)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn2.weight                loaded from layer1.2.bn2.weight          of shape (64,)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn3.bias                  loaded from layer1.2.bn3.bias            of shape (256,)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn3.weight                loaded from layer1.2.bn3.weight          of shape (256,)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.conv1.weight              loaded from layer1.2.conv1.weight        of shape (64, 256, 1, 1)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.conv2.weight              loaded from layer1.2.conv2.weight        of shape (64, 64, 3, 3)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.conv3.weight              loaded from layer1.2.conv3.weight        of shape (256, 64, 1, 1)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn1.bias                  loaded from layer2.0.bn1.bias            of shape (128,)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn1.weight                loaded from layer2.0.bn1.weight          of shape (128,)
2019-04-16 09:44:28,802 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn2.bias                  loaded from layer2.0.bn2.bias            of shape (128,)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn2.weight                loaded from layer2.0.bn2.weight          of shape (128,)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn3.bias                  loaded from layer2.0.bn3.bias            of shape (512,)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn3.weight                loaded from layer2.0.bn3.weight          of shape (512,)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.conv1.weight              loaded from layer2.0.conv1.weight        of shape (128, 256, 1, 1)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.conv2.weight              loaded from layer2.0.conv2.weight        of shape (128, 128, 3, 3)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.conv3.weight              loaded from layer2.0.conv3.weight        of shape (512, 128, 1, 1)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.downsample.0.weight       loaded from layer2.0.downsample.0.weight of shape (512, 256, 1, 1)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.downsample.1.bias         loaded from layer2.0.downsample.1.bias   of shape (512,)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.downsample.1.weight       loaded from layer2.0.downsample.1.weight of shape (512,)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn1.bias                  loaded from layer2.1.bn1.bias            of shape (128,)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn1.weight                loaded from layer2.1.bn1.weight          of shape (128,)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn2.bias                  loaded from layer2.1.bn2.bias            of shape (128,)
2019-04-16 09:44:28,803 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn2.weight                loaded from layer2.1.bn2.weight          of shape (128,)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn3.bias                  loaded from layer2.1.bn3.bias            of shape (512,)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn3.weight                loaded from layer2.1.bn3.weight          of shape (512,)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.conv1.weight              loaded from layer2.1.conv1.weight        of shape (128, 512, 1, 1)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.conv2.weight              loaded from layer2.1.conv2.weight        of shape (128, 128, 3, 3)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.conv3.weight              loaded from layer2.1.conv3.weight        of shape (512, 128, 1, 1)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn1.bias                  loaded from layer2.2.bn1.bias            of shape (128,)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn1.weight                loaded from layer2.2.bn1.weight          of shape (128,)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn2.bias                  loaded from layer2.2.bn2.bias            of shape (128,)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn2.weight                loaded from layer2.2.bn2.weight          of shape (128,)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn3.bias                  loaded from layer2.2.bn3.bias            of shape (512,)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn3.weight                loaded from layer2.2.bn3.weight          of shape (512,)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.conv1.weight              loaded from layer2.2.conv1.weight        of shape (128, 512, 1, 1)
2019-04-16 09:44:28,804 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.conv2.weight              loaded from layer2.2.conv2.weight        of shape (128, 128, 3, 3)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.conv3.weight              loaded from layer2.2.conv3.weight        of shape (512, 128, 1, 1)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn1.bias                  loaded from layer2.3.bn1.bias            of shape (128,)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn1.weight                loaded from layer2.3.bn1.weight          of shape (128,)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn2.bias                  loaded from layer2.3.bn2.bias            of shape (128,)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn2.weight                loaded from layer2.3.bn2.weight          of shape (128,)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn3.bias                  loaded from layer2.3.bn3.bias            of shape (512,)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn3.weight                loaded from layer2.3.bn3.weight          of shape (512,)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.conv1.weight              loaded from layer2.3.conv1.weight        of shape (128, 512, 1, 1)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.conv2.weight              loaded from layer2.3.conv2.weight        of shape (128, 128, 3, 3)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.conv3.weight              loaded from layer2.3.conv3.weight        of shape (512, 128, 1, 1)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn1.bias                  loaded from layer3.0.bn1.bias            of shape (256,)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn1.weight                loaded from layer3.0.bn1.weight          of shape (256,)
2019-04-16 09:44:28,805 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn2.bias                  loaded from layer3.0.bn2.bias            of shape (256,)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn2.weight                loaded from layer3.0.bn2.weight          of shape (256,)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn3.bias                  loaded from layer3.0.bn3.bias            of shape (1024,)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn3.weight                loaded from layer3.0.bn3.weight          of shape (1024,)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.conv1.weight              loaded from layer3.0.conv1.weight        of shape (256, 512, 1, 1)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.conv2.weight              loaded from layer3.0.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.conv3.weight              loaded from layer3.0.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.downsample.0.weight       loaded from layer3.0.downsample.0.weight of shape (1024, 512, 1, 1)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.downsample.1.bias         loaded from layer3.0.downsample.1.bias   of shape (1024,)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.downsample.1.weight       loaded from layer3.0.downsample.1.weight of shape (1024,)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn1.bias                  loaded from layer3.1.bn1.bias            of shape (256,)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn1.weight                loaded from layer3.1.bn1.weight          of shape (256,)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn2.bias                  loaded from layer3.1.bn2.bias            of shape (256,)
2019-04-16 09:44:28,806 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn2.weight                loaded from layer3.1.bn2.weight          of shape (256,)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn3.bias                  loaded from layer3.1.bn3.bias            of shape (1024,)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn3.weight                loaded from layer3.1.bn3.weight          of shape (1024,)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.conv1.weight              loaded from layer3.1.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.conv2.weight              loaded from layer3.1.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.conv3.weight              loaded from layer3.1.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn1.bias                  loaded from layer3.2.bn1.bias            of shape (256,)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn1.weight                loaded from layer3.2.bn1.weight          of shape (256,)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn2.bias                  loaded from layer3.2.bn2.bias            of shape (256,)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn2.weight                loaded from layer3.2.bn2.weight          of shape (256,)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn3.bias                  loaded from layer3.2.bn3.bias            of shape (1024,)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn3.weight                loaded from layer3.2.bn3.weight          of shape (1024,)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.conv1.weight              loaded from layer3.2.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 09:44:28,807 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.conv2.weight              loaded from layer3.2.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.conv3.weight              loaded from layer3.2.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn1.bias                  loaded from layer3.3.bn1.bias            of shape (256,)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn1.weight                loaded from layer3.3.bn1.weight          of shape (256,)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn2.bias                  loaded from layer3.3.bn2.bias            of shape (256,)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn2.weight                loaded from layer3.3.bn2.weight          of shape (256,)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn3.bias                  loaded from layer3.3.bn3.bias            of shape (1024,)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn3.weight                loaded from layer3.3.bn3.weight          of shape (1024,)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.conv1.weight              loaded from layer3.3.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.conv2.weight              loaded from layer3.3.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.conv3.weight              loaded from layer3.3.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn1.bias                  loaded from layer3.4.bn1.bias            of shape (256,)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn1.weight                loaded from layer3.4.bn1.weight          of shape (256,)
2019-04-16 09:44:28,808 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn2.bias                  loaded from layer3.4.bn2.bias            of shape (256,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn2.weight                loaded from layer3.4.bn2.weight          of shape (256,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn3.bias                  loaded from layer3.4.bn3.bias            of shape (1024,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn3.weight                loaded from layer3.4.bn3.weight          of shape (1024,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.conv1.weight              loaded from layer3.4.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.conv2.weight              loaded from layer3.4.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.conv3.weight              loaded from layer3.4.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn1.bias                  loaded from layer3.5.bn1.bias            of shape (256,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn1.weight                loaded from layer3.5.bn1.weight          of shape (256,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn2.bias                  loaded from layer3.5.bn2.bias            of shape (256,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn2.weight                loaded from layer3.5.bn2.weight          of shape (256,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn3.bias                  loaded from layer3.5.bn3.bias            of shape (1024,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn3.weight                loaded from layer3.5.bn3.weight          of shape (1024,)
2019-04-16 09:44:28,809 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.conv1.weight              loaded from layer3.5.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.conv2.weight              loaded from layer3.5.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.conv3.weight              loaded from layer3.5.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn1.bias                  loaded from layer4.0.bn1.bias            of shape (512,)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn1.weight                loaded from layer4.0.bn1.weight          of shape (512,)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn2.bias                  loaded from layer4.0.bn2.bias            of shape (512,)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn2.weight                loaded from layer4.0.bn2.weight          of shape (512,)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn3.bias                  loaded from layer4.0.bn3.bias            of shape (2048,)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn3.weight                loaded from layer4.0.bn3.weight          of shape (2048,)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.conv1.weight              loaded from layer4.0.conv1.weight        of shape (512, 1024, 1, 1)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.conv2.weight              loaded from layer4.0.conv2.weight        of shape (512, 512, 3, 3)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.conv3.weight              loaded from layer4.0.conv3.weight        of shape (2048, 512, 1, 1)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.downsample.0.weight       loaded from layer4.0.downsample.0.weight of shape (2048, 1024, 1, 1)
2019-04-16 09:44:28,810 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.downsample.1.bias         loaded from layer4.0.downsample.1.bias   of shape (2048,)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.downsample.1.weight       loaded from layer4.0.downsample.1.weight of shape (2048,)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn1.bias                  loaded from layer4.1.bn1.bias            of shape (512,)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn1.weight                loaded from layer4.1.bn1.weight          of shape (512,)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn2.bias                  loaded from layer4.1.bn2.bias            of shape (512,)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn2.weight                loaded from layer4.1.bn2.weight          of shape (512,)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn3.bias                  loaded from layer4.1.bn3.bias            of shape (2048,)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn3.weight                loaded from layer4.1.bn3.weight          of shape (2048,)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.conv1.weight              loaded from layer4.1.conv1.weight        of shape (512, 2048, 1, 1)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.conv2.weight              loaded from layer4.1.conv2.weight        of shape (512, 512, 3, 3)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.conv3.weight              loaded from layer4.1.conv3.weight        of shape (2048, 512, 1, 1)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn1.bias                  loaded from layer4.2.bn1.bias            of shape (512,)
2019-04-16 09:44:28,811 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn1.weight                loaded from layer4.2.bn1.weight          of shape (512,)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn2.bias                  loaded from layer4.2.bn2.bias            of shape (512,)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn2.weight                loaded from layer4.2.bn2.weight          of shape (512,)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn3.bias                  loaded from layer4.2.bn3.bias            of shape (2048,)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn3.weight                loaded from layer4.2.bn3.weight          of shape (2048,)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.conv1.weight              loaded from layer4.2.conv1.weight        of shape (512, 2048, 1, 1)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.conv2.weight              loaded from layer4.2.conv2.weight        of shape (512, 512, 3, 3)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.conv3.weight              loaded from layer4.2.conv3.weight        of shape (2048, 512, 1, 1)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.stem.bn1.bias                      loaded from bn1.bias                     of shape (64,)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.stem.bn1.weight                    loaded from bn1.weight                   of shape (64,)
2019-04-16 09:44:28,812 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.stem.conv1.weight                  loaded from conv1.weight                 of shape (64, 3, 7, 7)
When using more than one image per GPU you may encounter an out-of-memory (OOM) error if your GPU does not have sufficient memory. If this happens, you can reduce SOLVER.IMS_PER_BATCH (for training) or TEST.IMS_PER_BATCH (for inference). For training, you must also adjust the learning rate and schedule length according to the linear scaling rule. See for example: https://github.com/facebookresearch/Detectron/blob/master/configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml#L14
When using more than one image per GPU you may encounter an out-of-memory (OOM) error if your GPU does not have sufficient memory. If this happens, you can reduce SOLVER.IMS_PER_BATCH (for training) or TEST.IMS_PER_BATCH (for inference). For training, you must also adjust the learning rate and schedule length according to the linear scaling rule. See for example: https://github.com/facebookresearch/Detectron/blob/master/configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml#L14
When using more than one image per GPU you may encounter an out-of-memory (OOM) error if your GPU does not have sufficient memory. If this happens, you can reduce SOLVER.IMS_PER_BATCH (for training) or TEST.IMS_PER_BATCH (for inference). For training, you must also adjust the learning rate and schedule length according to the linear scaling rule. See for example: https://github.com/facebookresearch/Detectron/blob/master/configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml#L14
2019-04-16 09:44:28,848 maskrcnn_benchmark.data.build WARNING: When using more than one image per GPU you may encounter an out-of-memory (OOM) error if your GPU does not have sufficient memory. If this happens, you can reduce SOLVER.IMS_PER_BATCH (for training) or TEST.IMS_PER_BATCH (for inference). For training, you must also adjust the learning rate and schedule length according to the linear scaling rule. See for example: https://github.com/facebookresearch/Detectron/blob/master/configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml#L14
loading annotations into memory...
loading annotations into memory...
loading annotations into memory...
loading annotations into memory...
Done (t=11.84s)
creating index...
Done (t=11.89s)
creating index...
Done (t=11.91s)
creating index...
Done (t=12.02s)
creating index...
index created!
index created!
index created!
index created!
loading annotations into memory...
loading annotations into memory...
loading annotations into memory...
loading annotations into memory...
Done (t=4.65s)
creating index...
Done (t=4.64s)
creating index...
index created!
Done (t=4.84s)
creating index...
index created!
Done (t=4.77s)
creating index...
index created!
index created!
2019-04-16 09:44:48,874 maskrcnn_benchmark.trainer INFO: Start training
2019-04-16 09:45:04,999 maskrcnn_benchmark.trainer INFO: eta: 20:09:01  iter: 20  loss: 4.2540 (4.8868)  loss_centerness: 0.6721 (0.6827)  loss_cls: 1.0426 (1.0449)  loss_reg: 2.5388 (3.1591)  time: 0.6950 (0.8062)  data: 0.0225 (0.0672)  lr: 0.003333  max mem: 7051
2019-04-16 09:45:19,617 maskrcnn_benchmark.trainer INFO: eta: 19:12:17  iter: 40  loss: 3.1588 (4.0368)  loss_centerness: 0.6638 (0.6733)  loss_cls: 0.8076 (0.9305)  loss_reg: 1.6586 (2.4331)  time: 0.6950 (0.7685)  data: 0.0278 (0.0478)  lr: 0.003333  max mem: 7051
2019-04-16 09:45:33,480 maskrcnn_benchmark.trainer INFO: eta: 18:34:23  iter: 60  loss: 2.9134 (3.6434)  loss_centerness: 0.6611 (0.6692)  loss_cls: 0.7650 (0.8791)  loss_reg: 1.4770 (2.0951)  time: 0.6922 (0.7434)  data: 0.0308 (0.0417)  lr: 0.003333  max mem: 7051
2019-04-16 09:45:47,101 maskrcnn_benchmark.trainer INFO: eta: 18:10:46  iter: 80  loss: nan (nan)  loss_centerness: 0.6573 (nan)  loss_cls: 0.7112 (nan)  loss_reg: 0.9977 (nan)  time: 0.6785 (0.7278)  data: 0.0283 (0.0387)  lr: 0.003333  max mem: 7051
2019-04-16 09:46:00,404 maskrcnn_benchmark.trainer INFO: eta: 17:51:44  iter: 100  loss: nan (nan)  loss_centerness: nan (nan)  loss_cls: nan (nan)  loss_reg: nan (nan)  time: 0.6631 (0.7153)  data: 0.0248 (0.0361)  lr: 0.003333  max mem: 7051

Thank u for your helping

@tianzhi0549
Copy link
Owner

tianzhi0549 commented Apr 16, 2019 •
edited
Loading

Can you try to use python2.7? Our code is only tested with python2.7.

@bei-startdt
Copy link
Author

oh... It might be some different 3.6(I use) and 2.7. I will try with 2.7 and post my result after a later.

@bei-startdt
Copy link
Author 

No handlers could be found for logger "maskrcnn_benchmark"
No handlers could be found for logger "maskrcnn_benchmark"
2019-04-16 10:33:09,935 maskrcnn_benchmark INFO: Using 4 GPUs
No handlers could be found for logger "maskrcnn_benchmark"
2019-04-16 10:33:09,935 maskrcnn_benchmark INFO: Namespace(config_file='configs/fcos/fcos_R_50_FPN_1x.yaml', distributed=True, local_rank=0, opts=['DATALOADER.NUM_WORKERS', '2', 'OUTPUT_DIR', 'training_dir/fcos_R_50_FPN_1x'], skip_test=True)
2019-04-16 10:33:09,936 maskrcnn_benchmark INFO: Collecting env info (might take some time)
2019-04-16 10:33:12,610 maskrcnn_benchmark INFO:
PyTorch version: 1.0.0
Is debug build: No
CUDA used to build PyTorch: 9.0.176

OS: Ubuntu 16.04.6 LTS
GCC version: (Ubuntu 5.4.0-6ubuntu1~16.04.11) 5.4.0 20160609
CMake version: Could not collect

Python version: 2.7
Is CUDA available: Yes
CUDA runtime version: Could not collect
GPU models and configuration:
GPU 0: GeForce GTX 1080 Ti
GPU 1: GeForce GTX 1080 Ti
GPU 2: GeForce GTX 1080 Ti
GPU 3: GeForce GTX 1080 Ti
GPU 4: GeForce GTX 1080 Ti
GPU 5: GeForce GTX 1080 Ti
GPU 6: GeForce GTX 1080 Ti
GPU 7: GeForce GTX 1080 Ti

Nvidia driver version: 415.27
cuDNN version: Could not collect

Versions of relevant libraries:
[pip] Could not collect
[conda] torch                     1.0.0                    pypi_0    pypi
[conda] torchvision               0.2.2.post3              pypi_0    pypi
        Pillow (6.0.0)
2019-04-16 10:33:12,610 maskrcnn_benchmark INFO: Loaded configuration file configs/fcos/fcos_R_50_FPN_1x.yaml
2019-04-16 10:33:12,610 maskrcnn_benchmark INFO:
MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50"
  RPN_ONLY: True
  FCOS_ON: True
  BACKBONE:
    CONV_BODY: "R-50-FPN-RETINANET"
  RESNETS:
    BACKBONE_OUT_CHANNELS: 256
  RETINANET:
    USE_C5: False # FCOS uses P5 instead of C5
DATASETS:
  TRAIN: ("coco_2014_train", "coco_2014_valminusminival")
  TEST: ("coco_2014_minival",)
INPUT:
  MIN_SIZE_TRAIN: (800,)
  MAX_SIZE_TRAIN: 1333
  MIN_SIZE_TEST: 800
  MAX_SIZE_TEST: 1333
DATALOADER:
  SIZE_DIVISIBILITY: 32
SOLVER:
  BASE_LR: 0.01
  WEIGHT_DECAY: 0.0001
  STEPS: (60000, 80000)
  MAX_ITER: 90000
  IMS_PER_BATCH: 16
  WARMUP_METHOD: "constant"

2019-04-16 10:33:12,611 maskrcnn_benchmark INFO: Running with config:
DATALOADER:
  ASPECT_RATIO_GROUPING: True
  NUM_WORKERS: 2
  SIZE_DIVISIBILITY: 32
DATASETS:
  TEST: ('coco_2014_minival',)
  TRAIN: ('coco_2014_train', 'coco_2014_valminusminival')
INPUT:
  MAX_SIZE_TEST: 1333
  MAX_SIZE_TRAIN: 1333
  MIN_SIZE_RANGE_TRAIN: (-1, -1)
  MIN_SIZE_TEST: 800
  MIN_SIZE_TRAIN: (800,)
  PIXEL_MEAN: [102.9801, 115.9465, 122.7717]
  PIXEL_STD: [1.0, 1.0, 1.0]
  TO_BGR255: True
MODEL:
  BACKBONE:
    CONV_BODY: R-50-FPN-RETINANET
    FREEZE_CONV_BODY_AT: 2
    USE_GN: False
  CLS_AGNOSTIC_BBOX_REG: False
  DEVICE: cuda
  FBNET:
    ARCH: default
    ARCH_DEF:
    BN_TYPE: bn
    DET_HEAD_BLOCKS: []
    DET_HEAD_LAST_SCALE: 1.0
    DET_HEAD_STRIDE: 0
    DW_CONV_SKIP_BN: True
    DW_CONV_SKIP_RELU: True
    KPTS_HEAD_BLOCKS: []
    KPTS_HEAD_LAST_SCALE: 0.0
    KPTS_HEAD_STRIDE: 0
    MASK_HEAD_BLOCKS: []
    MASK_HEAD_LAST_SCALE: 0.0
    MASK_HEAD_STRIDE: 0
    RPN_BN_TYPE:
    RPN_HEAD_BLOCKS: 0
    SCALE_FACTOR: 1.0
    WIDTH_DIVISOR: 1
  FCOS:
    FPN_STRIDES: [8, 16, 32, 64, 128]
    INFERENCE_TH: 0.05
    LOSS_ALPHA: 0.25
    LOSS_GAMMA: 2.0
    NMS_TH: 0.4
    NUM_CLASSES: 81
    NUM_CONVS: 4
    PRE_NMS_TOP_N: 1000
    PRIOR_PROB: 0.01
  FCOS_ON: True
  FPN:
    USE_GN: False
    USE_RELU: False
  GROUP_NORM:
    DIM_PER_GP: -1
    EPSILON: 1e-05
    NUM_GROUPS: 32
  KEYPOINT_ON: False
  MASK_ON: False
  META_ARCHITECTURE: GeneralizedRCNN
  RESNETS:
    BACKBONE_OUT_CHANNELS: 256
    NUM_GROUPS: 1
    RES2_OUT_CHANNELS: 256
    RES5_DILATION: 1
    STEM_FUNC: StemWithFixedBatchNorm
    STEM_OUT_CHANNELS: 64
    STRIDE_IN_1X1: True
    TRANS_FUNC: BottleneckWithFixedBatchNorm
    WIDTH_PER_GROUP: 64
  RETINANET:
    ANCHOR_SIZES: (32, 64, 128, 256, 512)
    ANCHOR_STRIDES: (8, 16, 32, 64, 128)
    ASPECT_RATIOS: (0.5, 1.0, 2.0)
    BBOX_REG_BETA: 0.11
    BBOX_REG_WEIGHT: 4.0
    BG_IOU_THRESHOLD: 0.4
    FG_IOU_THRESHOLD: 0.5
    INFERENCE_TH: 0.05
    LOSS_ALPHA: 0.25
    LOSS_GAMMA: 2.0
    NMS_TH: 0.4
    NUM_CLASSES: 81
    NUM_CONVS: 4
    OCTAVE: 2.0
    PRE_NMS_TOP_N: 1000
    PRIOR_PROB: 0.01
    SCALES_PER_OCTAVE: 3
    STRADDLE_THRESH: 0
    USE_C5: False
  RETINANET_ON: False
  ROI_BOX_HEAD:
    CONV_HEAD_DIM: 256
    DILATION: 1
    FEATURE_EXTRACTOR: ResNet50Conv5ROIFeatureExtractor
    MLP_HEAD_DIM: 1024
    NUM_CLASSES: 81
    NUM_STACKED_CONVS: 4
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_SCALES: (0.0625,)
    PREDICTOR: FastRCNNPredictor
    USE_GN: False
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 512
    BBOX_REG_WEIGHTS: (10.0, 10.0, 5.0, 5.0)
    BG_IOU_THRESHOLD: 0.5
    DETECTIONS_PER_IMG: 100
    FG_IOU_THRESHOLD: 0.5
    NMS: 0.5
    POSITIVE_FRACTION: 0.25
    SCORE_THRESH: 0.05
    USE_FPN: False
  ROI_KEYPOINT_HEAD:
    CONV_LAYERS: (512, 512, 512, 512, 512, 512, 512, 512)
    FEATURE_EXTRACTOR: KeypointRCNNFeatureExtractor
    MLP_HEAD_DIM: 1024
    NUM_CLASSES: 17
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_SCALES: (0.0625,)
    PREDICTOR: KeypointRCNNPredictor
    RESOLUTION: 14
    SHARE_BOX_FEATURE_EXTRACTOR: True
  ROI_MASK_HEAD:
    CONV_LAYERS: (256, 256, 256, 256)
    DILATION: 1
    FEATURE_EXTRACTOR: ResNet50Conv5ROIFeatureExtractor
    MLP_HEAD_DIM: 1024
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_SCALES: (0.0625,)
    POSTPROCESS_MASKS: False
    POSTPROCESS_MASKS_THRESHOLD: 0.5
    PREDICTOR: MaskRCNNC4Predictor
    RESOLUTION: 14
    SHARE_BOX_FEATURE_EXTRACTOR: True
    USE_GN: False
  RPN:
    ANCHOR_SIZES: (32, 64, 128, 256, 512)
    ANCHOR_STRIDE: (16,)
    ASPECT_RATIOS: (0.5, 1.0, 2.0)
    BATCH_SIZE_PER_IMAGE: 256
    BG_IOU_THRESHOLD: 0.3
    FG_IOU_THRESHOLD: 0.7
    FPN_POST_NMS_TOP_N_TEST: 2000
    FPN_POST_NMS_TOP_N_TRAIN: 2000
    MIN_SIZE: 0
    NMS_THRESH: 0.7
    POSITIVE_FRACTION: 0.5
    POST_NMS_TOP_N_TEST: 1000
    POST_NMS_TOP_N_TRAIN: 2000
    PRE_NMS_TOP_N_TEST: 6000
    PRE_NMS_TOP_N_TRAIN: 12000
    RPN_HEAD: SingleConvRPNHead
    STRADDLE_THRESH: 0
    USE_FPN: False
  RPN_ONLY: True
  WEIGHT: catalog://ImageNetPretrained/MSRA/R-50
OUTPUT_DIR: training_dir/fcos_R_50_FPN_1x
PATHS_CATALOG: /data/bei/FCOS/maskrcnn_benchmark/config/paths_catalog.py
SOLVER:
  BASE_LR: 0.01
  BIAS_LR_FACTOR: 2
  CHECKPOINT_PERIOD: 2500
  GAMMA: 0.1
  IMS_PER_BATCH: 16
  MAX_ITER: 90000
  MOMENTUM: 0.9
  STEPS: (60000, 80000)
  WARMUP_FACTOR: 0.333333333333
  WARMUP_ITERS: 500
  WARMUP_METHOD: constant
  WEIGHT_DECAY: 0.0001
  WEIGHT_DECAY_BIAS: 0
TEST:
  DETECTIONS_PER_IMG: 100
  EXPECTED_RESULTS: []
  EXPECTED_RESULTS_SIGMA_TOL: 4
  IMS_PER_BATCH: 8
2019-04-16 10:33:13,403 maskrcnn_benchmark.utils.checkpoint INFO: Loading checkpoint from catalog://ImageNetPretrained/MSRA/R-50
2019-04-16 10:33:13,404 maskrcnn_benchmark.utils.checkpoint INFO: catalog://ImageNetPretrained/MSRA/R-50 points to https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl
2019-04-16 10:33:13,442 maskrcnn_benchmark.utils.checkpoint INFO: url https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/MSRA/R-50.pkl cached in /home/wangjiangben/.torch/models/R-50.pkl
2019-04-16 10:33:13,495 maskrcnn_benchmark.utils.c2_model_loading INFO: Remapping C2 weights
2019-04-16 10:33:13,496 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: conv1_b              mapped name: conv1.bias
2019-04-16 10:33:13,496 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: conv1_w              mapped name: conv1.weight
2019-04-16 10:33:13,496 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: fc1000_b             mapped name: fc1000.bias
2019-04-16 10:33:13,496 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: fc1000_w             mapped name: fc1000.weight
2019-04-16 10:33:13,496 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_b     mapped name: layer1.0.downsample.0.bias
2019-04-16 10:33:13,496 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_bn_b  mapped name: layer1.0.downsample.1.bias
2019-04-16 10:33:13,496 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_bn_s  mapped name: layer1.0.downsample.1.weight
2019-04-16 10:33:13,496 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch1_w     mapped name: layer1.0.downsample.0.weight
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_b    mapped name: layer1.0.conv1.bias
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_bn_b mapped name: layer1.0.bn1.bias
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_bn_s mapped name: layer1.0.bn1.weight
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2a_w    mapped name: layer1.0.conv1.weight
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_b    mapped name: layer1.0.conv2.bias
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_bn_b mapped name: layer1.0.bn2.bias
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_bn_s mapped name: layer1.0.bn2.weight
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2b_w    mapped name: layer1.0.conv2.weight
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_b    mapped name: layer1.0.conv3.bias
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_bn_b mapped name: layer1.0.bn3.bias
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_bn_s mapped name: layer1.0.bn3.weight
2019-04-16 10:33:13,497 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_0_branch2c_w    mapped name: layer1.0.conv3.weight
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_b    mapped name: layer1.1.conv1.bias
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_bn_b mapped name: layer1.1.bn1.bias
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_bn_s mapped name: layer1.1.bn1.weight
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2a_w    mapped name: layer1.1.conv1.weight
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_b    mapped name: layer1.1.conv2.bias
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_bn_b mapped name: layer1.1.bn2.bias
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_bn_s mapped name: layer1.1.bn2.weight
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2b_w    mapped name: layer1.1.conv2.weight
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_b    mapped name: layer1.1.conv3.bias
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_bn_b mapped name: layer1.1.bn3.bias
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_bn_s mapped name: layer1.1.bn3.weight
2019-04-16 10:33:13,498 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_1_branch2c_w    mapped name: layer1.1.conv3.weight
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_b    mapped name: layer1.2.conv1.bias
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_bn_b mapped name: layer1.2.bn1.bias
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_bn_s mapped name: layer1.2.bn1.weight
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2a_w    mapped name: layer1.2.conv1.weight
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_b    mapped name: layer1.2.conv2.bias
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_bn_b mapped name: layer1.2.bn2.bias
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_bn_s mapped name: layer1.2.bn2.weight
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2b_w    mapped name: layer1.2.conv2.weight
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_b    mapped name: layer1.2.conv3.bias
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_bn_b mapped name: layer1.2.bn3.bias
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_bn_s mapped name: layer1.2.bn3.weight
2019-04-16 10:33:13,499 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res2_2_branch2c_w    mapped name: layer1.2.conv3.weight
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_b     mapped name: layer2.0.downsample.0.bias
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_bn_b  mapped name: layer2.0.downsample.1.bias
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_bn_s  mapped name: layer2.0.downsample.1.weight
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch1_w     mapped name: layer2.0.downsample.0.weight
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_b    mapped name: layer2.0.conv1.bias
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_bn_b mapped name: layer2.0.bn1.bias
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_bn_s mapped name: layer2.0.bn1.weight
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2a_w    mapped name: layer2.0.conv1.weight
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_b    mapped name: layer2.0.conv2.bias
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_bn_b mapped name: layer2.0.bn2.bias
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_bn_s mapped name: layer2.0.bn2.weight
2019-04-16 10:33:13,500 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2b_w    mapped name: layer2.0.conv2.weight
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_b    mapped name: layer2.0.conv3.bias
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_bn_b mapped name: layer2.0.bn3.bias
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_bn_s mapped name: layer2.0.bn3.weight
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_0_branch2c_w    mapped name: layer2.0.conv3.weight
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_b    mapped name: layer2.1.conv1.bias
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_bn_b mapped name: layer2.1.bn1.bias
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_bn_s mapped name: layer2.1.bn1.weight
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2a_w    mapped name: layer2.1.conv1.weight
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_b    mapped name: layer2.1.conv2.bias
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_bn_b mapped name: layer2.1.bn2.bias
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_bn_s mapped name: layer2.1.bn2.weight
2019-04-16 10:33:13,501 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2b_w    mapped name: layer2.1.conv2.weight
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_b    mapped name: layer2.1.conv3.bias
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_bn_b mapped name: layer2.1.bn3.bias
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_bn_s mapped name: layer2.1.bn3.weight
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_1_branch2c_w    mapped name: layer2.1.conv3.weight
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_b    mapped name: layer2.2.conv1.bias
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_bn_b mapped name: layer2.2.bn1.bias
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_bn_s mapped name: layer2.2.bn1.weight
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2a_w    mapped name: layer2.2.conv1.weight
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_b    mapped name: layer2.2.conv2.bias
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_bn_b mapped name: layer2.2.bn2.bias
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_bn_s mapped name: layer2.2.bn2.weight
2019-04-16 10:33:13,502 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2b_w    mapped name: layer2.2.conv2.weight
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_b    mapped name: layer2.2.conv3.bias
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_bn_b mapped name: layer2.2.bn3.bias
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_bn_s mapped name: layer2.2.bn3.weight
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_2_branch2c_w    mapped name: layer2.2.conv3.weight
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_b    mapped name: layer2.3.conv1.bias
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_bn_b mapped name: layer2.3.bn1.bias
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_bn_s mapped name: layer2.3.bn1.weight
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2a_w    mapped name: layer2.3.conv1.weight
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_b    mapped name: layer2.3.conv2.bias
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_bn_b mapped name: layer2.3.bn2.bias
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_bn_s mapped name: layer2.3.bn2.weight
2019-04-16 10:33:13,503 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2b_w    mapped name: layer2.3.conv2.weight
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_b    mapped name: layer2.3.conv3.bias
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_bn_b mapped name: layer2.3.bn3.bias
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_bn_s mapped name: layer2.3.bn3.weight
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res3_3_branch2c_w    mapped name: layer2.3.conv3.weight
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_b     mapped name: layer3.0.downsample.0.bias
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_bn_b  mapped name: layer3.0.downsample.1.bias
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_bn_s  mapped name: layer3.0.downsample.1.weight
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch1_w     mapped name: layer3.0.downsample.0.weight
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_b    mapped name: layer3.0.conv1.bias
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_bn_b mapped name: layer3.0.bn1.bias
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_bn_s mapped name: layer3.0.bn1.weight
2019-04-16 10:33:13,504 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2a_w    mapped name: layer3.0.conv1.weight
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_b    mapped name: layer3.0.conv2.bias
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_bn_b mapped name: layer3.0.bn2.bias
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_bn_s mapped name: layer3.0.bn2.weight
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2b_w    mapped name: layer3.0.conv2.weight
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_b    mapped name: layer3.0.conv3.bias
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_bn_b mapped name: layer3.0.bn3.bias
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_bn_s mapped name: layer3.0.bn3.weight
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_0_branch2c_w    mapped name: layer3.0.conv3.weight
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_b    mapped name: layer3.1.conv1.bias
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_bn_b mapped name: layer3.1.bn1.bias
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_bn_s mapped name: layer3.1.bn1.weight
2019-04-16 10:33:13,505 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2a_w    mapped name: layer3.1.conv1.weight
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_b    mapped name: layer3.1.conv2.bias
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_bn_b mapped name: layer3.1.bn2.bias
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_bn_s mapped name: layer3.1.bn2.weight
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2b_w    mapped name: layer3.1.conv2.weight
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_b    mapped name: layer3.1.conv3.bias
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_bn_b mapped name: layer3.1.bn3.bias
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_bn_s mapped name: layer3.1.bn3.weight
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_1_branch2c_w    mapped name: layer3.1.conv3.weight
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_b    mapped name: layer3.2.conv1.bias
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_bn_b mapped name: layer3.2.bn1.bias
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_bn_s mapped name: layer3.2.bn1.weight
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2a_w    mapped name: layer3.2.conv1.weight
2019-04-16 10:33:13,506 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_b    mapped name: layer3.2.conv2.bias
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_bn_b mapped name: layer3.2.bn2.bias
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_bn_s mapped name: layer3.2.bn2.weight
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2b_w    mapped name: layer3.2.conv2.weight
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_b    mapped name: layer3.2.conv3.bias
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_bn_b mapped name: layer3.2.bn3.bias
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_bn_s mapped name: layer3.2.bn3.weight
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_2_branch2c_w    mapped name: layer3.2.conv3.weight
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_b    mapped name: layer3.3.conv1.bias
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_bn_b mapped name: layer3.3.bn1.bias
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_bn_s mapped name: layer3.3.bn1.weight
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2a_w    mapped name: layer3.3.conv1.weight
2019-04-16 10:33:13,507 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_b    mapped name: layer3.3.conv2.bias
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_bn_b mapped name: layer3.3.bn2.bias
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_bn_s mapped name: layer3.3.bn2.weight
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2b_w    mapped name: layer3.3.conv2.weight
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_b    mapped name: layer3.3.conv3.bias
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_bn_b mapped name: layer3.3.bn3.bias
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_bn_s mapped name: layer3.3.bn3.weight
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_3_branch2c_w    mapped name: layer3.3.conv3.weight
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_b    mapped name: layer3.4.conv1.bias
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_bn_b mapped name: layer3.4.bn1.bias
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_bn_s mapped name: layer3.4.bn1.weight
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2a_w    mapped name: layer3.4.conv1.weight
2019-04-16 10:33:13,508 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_b    mapped name: layer3.4.conv2.bias
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_bn_b mapped name: layer3.4.bn2.bias
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_bn_s mapped name: layer3.4.bn2.weight
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2b_w    mapped name: layer3.4.conv2.weight
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_b    mapped name: layer3.4.conv3.bias
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_bn_b mapped name: layer3.4.bn3.bias
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_bn_s mapped name: layer3.4.bn3.weight
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_4_branch2c_w    mapped name: layer3.4.conv3.weight
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_b    mapped name: layer3.5.conv1.bias
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_bn_b mapped name: layer3.5.bn1.bias
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_bn_s mapped name: layer3.5.bn1.weight
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2a_w    mapped name: layer3.5.conv1.weight
2019-04-16 10:33:13,509 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_b    mapped name: layer3.5.conv2.bias
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_bn_b mapped name: layer3.5.bn2.bias
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_bn_s mapped name: layer3.5.bn2.weight
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2b_w    mapped name: layer3.5.conv2.weight
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_b    mapped name: layer3.5.conv3.bias
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_bn_b mapped name: layer3.5.bn3.bias
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_bn_s mapped name: layer3.5.bn3.weight
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res4_5_branch2c_w    mapped name: layer3.5.conv3.weight
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_b     mapped name: layer4.0.downsample.0.bias
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_bn_b  mapped name: layer4.0.downsample.1.bias
2019-04-16 10:33:13,510 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_bn_s  mapped name: layer4.0.downsample.1.weight
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch1_w     mapped name: layer4.0.downsample.0.weight
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_b    mapped name: layer4.0.conv1.bias
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_bn_b mapped name: layer4.0.bn1.bias
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_bn_s mapped name: layer4.0.bn1.weight
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2a_w    mapped name: layer4.0.conv1.weight
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_b    mapped name: layer4.0.conv2.bias
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_bn_b mapped name: layer4.0.bn2.bias
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_bn_s mapped name: layer4.0.bn2.weight
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2b_w    mapped name: layer4.0.conv2.weight
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_b    mapped name: layer4.0.conv3.bias
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_bn_b mapped name: layer4.0.bn3.bias
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_bn_s mapped name: layer4.0.bn3.weight
2019-04-16 10:33:13,511 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_0_branch2c_w    mapped name: layer4.0.conv3.weight
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_b    mapped name: layer4.1.conv1.bias
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_bn_b mapped name: layer4.1.bn1.bias
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_bn_s mapped name: layer4.1.bn1.weight
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2a_w    mapped name: layer4.1.conv1.weight
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_b    mapped name: layer4.1.conv2.bias
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_bn_b mapped name: layer4.1.bn2.bias
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_bn_s mapped name: layer4.1.bn2.weight
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2b_w    mapped name: layer4.1.conv2.weight
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_b    mapped name: layer4.1.conv3.bias
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_bn_b mapped name: layer4.1.bn3.bias
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_bn_s mapped name: layer4.1.bn3.weight
2019-04-16 10:33:13,512 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_1_branch2c_w    mapped name: layer4.1.conv3.weight
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_b    mapped name: layer4.2.conv1.bias
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_bn_b mapped name: layer4.2.bn1.bias
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_bn_s mapped name: layer4.2.bn1.weight
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2a_w    mapped name: layer4.2.conv1.weight
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_b    mapped name: layer4.2.conv2.bias
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_bn_b mapped name: layer4.2.bn2.bias
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_bn_s mapped name: layer4.2.bn2.weight
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2b_w    mapped name: layer4.2.conv2.weight
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_b    mapped name: layer4.2.conv3.bias
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_bn_b mapped name: layer4.2.bn3.bias
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_bn_s mapped name: layer4.2.bn3.weight
2019-04-16 10:33:13,513 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res5_2_branch2c_w    mapped name: layer4.2.conv3.weight
2019-04-16 10:33:13,514 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res_conv1_bn_b       mapped name: bn1.bias
2019-04-16 10:33:13,514 maskrcnn_benchmark.utils.c2_model_loading INFO: C2 name: res_conv1_bn_s       mapped name: bn1.weight
2019-04-16 10:33:13,546 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn1.bias                  loaded from layer1.0.bn1.bias            of shape (64,)
2019-04-16 10:33:13,546 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn1.weight                loaded from layer1.0.bn1.weight          of shape (64,)
2019-04-16 10:33:13,546 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn2.bias                  loaded from layer1.0.bn2.bias            of shape (64,)
2019-04-16 10:33:13,546 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn2.weight                loaded from layer1.0.bn2.weight          of shape (64,)
2019-04-16 10:33:13,546 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn3.bias                  loaded from layer1.0.bn3.bias            of shape (256,)
2019-04-16 10:33:13,546 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.bn3.weight                loaded from layer1.0.bn3.weight          of shape (256,)
2019-04-16 10:33:13,546 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.conv1.weight              loaded from layer1.0.conv1.weight        of shape (64, 64, 1, 1)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.conv2.weight              loaded from layer1.0.conv2.weight        of shape (64, 64, 3, 3)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.conv3.weight              loaded from layer1.0.conv3.weight        of shape (256, 64, 1, 1)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.downsample.0.weight       loaded from layer1.0.downsample.0.weight of shape (256, 64, 1, 1)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.downsample.1.bias         loaded from layer1.0.downsample.1.bias   of shape (256,)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.0.downsample.1.weight       loaded from layer1.0.downsample.1.weight of shape (256,)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn1.bias                  loaded from layer1.1.bn1.bias            of shape (64,)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn1.weight                loaded from layer1.1.bn1.weight          of shape (64,)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn2.bias                  loaded from layer1.1.bn2.bias            of shape (64,)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn2.weight                loaded from layer1.1.bn2.weight          of shape (64,)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn3.bias                  loaded from layer1.1.bn3.bias            of shape (256,)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.bn3.weight                loaded from layer1.1.bn3.weight          of shape (256,)
2019-04-16 10:33:13,547 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.conv1.weight              loaded from layer1.1.conv1.weight        of shape (64, 256, 1, 1)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.conv2.weight              loaded from layer1.1.conv2.weight        of shape (64, 64, 3, 3)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.1.conv3.weight              loaded from layer1.1.conv3.weight        of shape (256, 64, 1, 1)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn1.bias                  loaded from layer1.2.bn1.bias            of shape (64,)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn1.weight                loaded from layer1.2.bn1.weight          of shape (64,)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn2.bias                  loaded from layer1.2.bn2.bias            of shape (64,)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn2.weight                loaded from layer1.2.bn2.weight          of shape (64,)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn3.bias                  loaded from layer1.2.bn3.bias            of shape (256,)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.bn3.weight                loaded from layer1.2.bn3.weight          of shape (256,)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.conv1.weight              loaded from layer1.2.conv1.weight        of shape (64, 256, 1, 1)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.conv2.weight              loaded from layer1.2.conv2.weight        of shape (64, 64, 3, 3)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer1.2.conv3.weight              loaded from layer1.2.conv3.weight        of shape (256, 64, 1, 1)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn1.bias                  loaded from layer2.0.bn1.bias            of shape (128,)
2019-04-16 10:33:13,548 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn1.weight                loaded from layer2.0.bn1.weight          of shape (128,)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn2.bias                  loaded from layer2.0.bn2.bias            of shape (128,)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn2.weight                loaded from layer2.0.bn2.weight          of shape (128,)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn3.bias                  loaded from layer2.0.bn3.bias            of shape (512,)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.bn3.weight                loaded from layer2.0.bn3.weight          of shape (512,)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.conv1.weight              loaded from layer2.0.conv1.weight        of shape (128, 256, 1, 1)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.conv2.weight              loaded from layer2.0.conv2.weight        of shape (128, 128, 3, 3)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.conv3.weight              loaded from layer2.0.conv3.weight        of shape (512, 128, 1, 1)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.downsample.0.weight       loaded from layer2.0.downsample.0.weight of shape (512, 256, 1, 1)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.downsample.1.bias         loaded from layer2.0.downsample.1.bias   of shape (512,)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.0.downsample.1.weight       loaded from layer2.0.downsample.1.weight of shape (512,)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn1.bias                  loaded from layer2.1.bn1.bias            of shape (128,)
2019-04-16 10:33:13,549 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn1.weight                loaded from layer2.1.bn1.weight          of shape (128,)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn2.bias                  loaded from layer2.1.bn2.bias            of shape (128,)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn2.weight                loaded from layer2.1.bn2.weight          of shape (128,)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn3.bias                  loaded from layer2.1.bn3.bias            of shape (512,)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.bn3.weight                loaded from layer2.1.bn3.weight          of shape (512,)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.conv1.weight              loaded from layer2.1.conv1.weight        of shape (128, 512, 1, 1)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.conv2.weight              loaded from layer2.1.conv2.weight        of shape (128, 128, 3, 3)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.1.conv3.weight              loaded from layer2.1.conv3.weight        of shape (512, 128, 1, 1)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn1.bias                  loaded from layer2.2.bn1.bias            of shape (128,)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn1.weight                loaded from layer2.2.bn1.weight          of shape (128,)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn2.bias                  loaded from layer2.2.bn2.bias            of shape (128,)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn2.weight                loaded from layer2.2.bn2.weight          of shape (128,)
2019-04-16 10:33:13,550 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn3.bias                  loaded from layer2.2.bn3.bias            of shape (512,)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.bn3.weight                loaded from layer2.2.bn3.weight          of shape (512,)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.conv1.weight              loaded from layer2.2.conv1.weight        of shape (128, 512, 1, 1)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.conv2.weight              loaded from layer2.2.conv2.weight        of shape (128, 128, 3, 3)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.2.conv3.weight              loaded from layer2.2.conv3.weight        of shape (512, 128, 1, 1)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn1.bias                  loaded from layer2.3.bn1.bias            of shape (128,)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn1.weight                loaded from layer2.3.bn1.weight          of shape (128,)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn2.bias                  loaded from layer2.3.bn2.bias            of shape (128,)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn2.weight                loaded from layer2.3.bn2.weight          of shape (128,)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn3.bias                  loaded from layer2.3.bn3.bias            of shape (512,)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.bn3.weight                loaded from layer2.3.bn3.weight          of shape (512,)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.conv1.weight              loaded from layer2.3.conv1.weight        of shape (128, 512, 1, 1)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.conv2.weight              loaded from layer2.3.conv2.weight        of shape (128, 128, 3, 3)
2019-04-16 10:33:13,551 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer2.3.conv3.weight              loaded from layer2.3.conv3.weight        of shape (512, 128, 1, 1)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn1.bias                  loaded from layer3.0.bn1.bias            of shape (256,)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn1.weight                loaded from layer3.0.bn1.weight          of shape (256,)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn2.bias                  loaded from layer3.0.bn2.bias            of shape (256,)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn2.weight                loaded from layer3.0.bn2.weight          of shape (256,)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn3.bias                  loaded from layer3.0.bn3.bias            of shape (1024,)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.bn3.weight                loaded from layer3.0.bn3.weight          of shape (1024,)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.conv1.weight              loaded from layer3.0.conv1.weight        of shape (256, 512, 1, 1)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.conv2.weight              loaded from layer3.0.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.conv3.weight              loaded from layer3.0.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.downsample.0.weight       loaded from layer3.0.downsample.0.weight of shape (1024, 512, 1, 1)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.downsample.1.bias         loaded from layer3.0.downsample.1.bias   of shape (1024,)
2019-04-16 10:33:13,552 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.0.downsample.1.weight       loaded from layer3.0.downsample.1.weight of shape (1024,)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn1.bias                  loaded from layer3.1.bn1.bias            of shape (256,)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn1.weight                loaded from layer3.1.bn1.weight          of shape (256,)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn2.bias                  loaded from layer3.1.bn2.bias            of shape (256,)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn2.weight                loaded from layer3.1.bn2.weight          of shape (256,)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn3.bias                  loaded from layer3.1.bn3.bias            of shape (1024,)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.bn3.weight                loaded from layer3.1.bn3.weight          of shape (1024,)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.conv1.weight              loaded from layer3.1.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.conv2.weight              loaded from layer3.1.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.1.conv3.weight              loaded from layer3.1.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn1.bias                  loaded from layer3.2.bn1.bias            of shape (256,)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn1.weight                loaded from layer3.2.bn1.weight          of shape (256,)
2019-04-16 10:33:13,553 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn2.bias                  loaded from layer3.2.bn2.bias            of shape (256,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn2.weight                loaded from layer3.2.bn2.weight          of shape (256,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn3.bias                  loaded from layer3.2.bn3.bias            of shape (1024,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.bn3.weight                loaded from layer3.2.bn3.weight          of shape (1024,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.conv1.weight              loaded from layer3.2.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.conv2.weight              loaded from layer3.2.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.2.conv3.weight              loaded from layer3.2.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn1.bias                  loaded from layer3.3.bn1.bias            of shape (256,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn1.weight                loaded from layer3.3.bn1.weight          of shape (256,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn2.bias                  loaded from layer3.3.bn2.bias            of shape (256,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn2.weight                loaded from layer3.3.bn2.weight          of shape (256,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn3.bias                  loaded from layer3.3.bn3.bias            of shape (1024,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.bn3.weight                loaded from layer3.3.bn3.weight          of shape (1024,)
2019-04-16 10:33:13,554 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.conv1.weight              loaded from layer3.3.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.conv2.weight              loaded from layer3.3.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.3.conv3.weight              loaded from layer3.3.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn1.bias                  loaded from layer3.4.bn1.bias            of shape (256,)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn1.weight                loaded from layer3.4.bn1.weight          of shape (256,)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn2.bias                  loaded from layer3.4.bn2.bias            of shape (256,)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn2.weight                loaded from layer3.4.bn2.weight          of shape (256,)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn3.bias                  loaded from layer3.4.bn3.bias            of shape (1024,)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.bn3.weight                loaded from layer3.4.bn3.weight          of shape (1024,)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.conv1.weight              loaded from layer3.4.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.conv2.weight              loaded from layer3.4.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.4.conv3.weight              loaded from layer3.4.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 10:33:13,555 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn1.bias                  loaded from layer3.5.bn1.bias            of shape (256,)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn1.weight                loaded from layer3.5.bn1.weight          of shape (256,)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn2.bias                  loaded from layer3.5.bn2.bias            of shape (256,)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn2.weight                loaded from layer3.5.bn2.weight          of shape (256,)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn3.bias                  loaded from layer3.5.bn3.bias            of shape (1024,)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.bn3.weight                loaded from layer3.5.bn3.weight          of shape (1024,)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.conv1.weight              loaded from layer3.5.conv1.weight        of shape (256, 1024, 1, 1)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.conv2.weight              loaded from layer3.5.conv2.weight        of shape (256, 256, 3, 3)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer3.5.conv3.weight              loaded from layer3.5.conv3.weight        of shape (1024, 256, 1, 1)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn1.bias                  loaded from layer4.0.bn1.bias            of shape (512,)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn1.weight                loaded from layer4.0.bn1.weight          of shape (512,)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn2.bias                  loaded from layer4.0.bn2.bias            of shape (512,)
2019-04-16 10:33:13,556 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn2.weight                loaded from layer4.0.bn2.weight          of shape (512,)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn3.bias                  loaded from layer4.0.bn3.bias            of shape (2048,)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.bn3.weight                loaded from layer4.0.bn3.weight          of shape (2048,)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.conv1.weight              loaded from layer4.0.conv1.weight        of shape (512, 1024, 1, 1)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.conv2.weight              loaded from layer4.0.conv2.weight        of shape (512, 512, 3, 3)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.conv3.weight              loaded from layer4.0.conv3.weight        of shape (2048, 512, 1, 1)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.downsample.0.weight       loaded from layer4.0.downsample.0.weight of shape (2048, 1024, 1, 1)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.downsample.1.bias         loaded from layer4.0.downsample.1.bias   of shape (2048,)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.0.downsample.1.weight       loaded from layer4.0.downsample.1.weight of shape (2048,)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn1.bias                  loaded from layer4.1.bn1.bias            of shape (512,)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn1.weight                loaded from layer4.1.bn1.weight          of shape (512,)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn2.bias                  loaded from layer4.1.bn2.bias            of shape (512,)
2019-04-16 10:33:13,557 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn2.weight                loaded from layer4.1.bn2.weight          of shape (512,)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn3.bias                  loaded from layer4.1.bn3.bias            of shape (2048,)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.bn3.weight                loaded from layer4.1.bn3.weight          of shape (2048,)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.conv1.weight              loaded from layer4.1.conv1.weight        of shape (512, 2048, 1, 1)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.conv2.weight              loaded from layer4.1.conv2.weight        of shape (512, 512, 3, 3)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.1.conv3.weight              loaded from layer4.1.conv3.weight        of shape (2048, 512, 1, 1)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn1.bias                  loaded from layer4.2.bn1.bias            of shape (512,)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn1.weight                loaded from layer4.2.bn1.weight          of shape (512,)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn2.bias                  loaded from layer4.2.bn2.bias            of shape (512,)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn2.weight                loaded from layer4.2.bn2.weight          of shape (512,)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn3.bias                  loaded from layer4.2.bn3.bias            of shape (2048,)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.bn3.weight                loaded from layer4.2.bn3.weight          of shape (2048,)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.conv1.weight              loaded from layer4.2.conv1.weight        of shape (512, 2048, 1, 1)
2019-04-16 10:33:13,558 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.conv2.weight              loaded from layer4.2.conv2.weight        of shape (512, 512, 3, 3)
2019-04-16 10:33:13,559 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.layer4.2.conv3.weight              loaded from layer4.2.conv3.weight        of shape (2048, 512, 1, 1)
2019-04-16 10:33:13,559 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.stem.bn1.bias                      loaded from bn1.bias                     of shape (64,)
2019-04-16 10:33:13,559 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.stem.bn1.weight                    loaded from bn1.weight                   of shape (64,)
2019-04-16 10:33:13,559 maskrcnn_benchmark.utils.model_serialization INFO: module.backbone.body.stem.conv1.weight                  loaded from conv1.weight                 of shape (64, 3, 7, 7)
2019-04-16 10:33:13,611 maskrcnn_benchmark.data.build WARNING: When using more than one image per GPU you may encounter an out-of-memory (OOM) error if your GPU does not have sufficient memory. If this happens, you can reduce SOLVER.IMS_PER_BATCH (for training) or TEST.IMS_PER_BATCH (for inference). For training, you must also adjust the learning rate and schedule length according to the linear scaling rule. See for example: https://github.com/facebookresearch/Detectron/blob/master/configs/getting_started/tutorial_1gpu_e2e_faster_rcnn_R-50-FPN.yaml#L14
loading annotations into memory...loading annotations into memory...

loading annotations into memory...
loading annotations into memory...
Done (t=16.64s)
creating index...
Done (t=16.99s)
creating index...
Done (t=17.21s)
creating index...
Done (t=17.84s)
creating index...
index created!
index created!
index created!
loading annotations into memory...
index created!
loading annotations into memory...
loading annotations into memory...
loading annotations into memory...
Done (t=6.93s)
creating index...
Done (t=7.07s)
creating index...
Done (t=7.29s)
creating index...
Done (t=7.39s)
creating index...
index created!
index created!
2019-04-16 10:33:47,672 maskrcnn_benchmark.trainer INFO: Start training
index created!
index created!
2019-04-16 10:34:05,565 maskrcnn_benchmark.trainer INFO: eta: 22:21:28  iter: 20  loss: 4.3718 (5.2479)  loss_cls: 1.0199 (1.0036)  loss_centerness: 0.6694 (0.6730)  loss_reg: 2.6008 (3.5713)  time: 0.7003 (0.8945)  data: 0.0219 (0.0851)  lr: 0.003333  max mem: 7051
2019-04-16 10:34:20,310 maskrcnn_benchmark.trainer INFO: eta: 20:23:18  iter: 40  loss: 3.6584 (nan)  loss_cls: 0.8155 (nan)  loss_centerness: 0.6613 (nan)  loss_reg: 2.1678 (nan)  time: 0.6955 (0.8159)  data: 0.0235 (0.0542)  lr: 0.003333  max mem: 7051
2019-04-16 10:34:33,628 maskrcnn_benchmark.trainer INFO: eta: 19:08:05  iter: 60  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6679 (0.7659)  data: 0.0231 (0.0439)  lr: 0.003333  max mem: 7051
2019-04-16 10:34:46,920 maskrcnn_benchmark.trainer INFO: eta: 18:29:52  iter: 80  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6659 (0.7406)  data: 0.0225 (0.0390)  lr: 0.003333  max mem: 7051
2019-04-16 10:35:00,301 maskrcnn_benchmark.trainer INFO: eta: 18:08:11  iter: 100  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6678 (0.7263)  data: 0.0223 (0.0358)  lr: 0.003333  max mem: 7051
2019-04-16 10:35:13,445 maskrcnn_benchmark.trainer INFO: eta: 17:50:42  iter: 120  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6566 (0.7148)  data: 0.0222 (0.0340)  lr: 0.003333  max mem: 7051
2019-04-16 10:35:26,752 maskrcnn_benchmark.trainer INFO: eta: 17:39:53  iter: 140  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6618 (0.7077)  data: 0.0255 (0.0331)  lr: 0.003333  max mem: 7051
2019-04-16 10:35:40,196 maskrcnn_benchmark.trainer INFO: eta: 17:33:01  iter: 160  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6735 (0.7033)  data: 0.0239 (0.0320)  lr: 0.003333  max mem: 7051
2019-04-16 10:35:53,716 maskrcnn_benchmark.trainer INFO: eta: 17:28:14  iter: 180  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6763 (0.7002)  data: 0.0236 (0.0312)  lr: 0.003333  max mem: 7051
2019-04-16 10:36:07,115 maskrcnn_benchmark.trainer INFO: eta: 17:23:28  iter: 200  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6638 (0.6972)  data: 0.0252 (0.0307)  lr: 0.003333  max mem: 7051
2019-04-16 10:36:20,502 maskrcnn_benchmark.trainer INFO: eta: 17:19:27  iter: 220  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6729 (0.6947)  data: 0.0224 (0.0301)  lr: 0.003333  max mem: 7055
2019-04-16 10:36:33,843 maskrcnn_benchmark.trainer INFO: eta: 17:15:47  iter: 240  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6620 (0.6924)  data: 0.0225 (0.0296)  lr: 0.003333  max mem: 7055
2019-04-16 10:36:47,305 maskrcnn_benchmark.trainer INFO: eta: 17:13:20  iter: 260  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6750 (0.6909)  data: 0.0247 (0.0293)  lr: 0.003333  max mem: 7055
2019-04-16 10:37:00,747 maskrcnn_benchmark.trainer INFO: eta: 17:11:06  iter: 280  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6702 (0.6895)  data: 0.0248 (0.0290)  lr: 0.003333  max mem: 7055
2019-04-16 10:37:14,164 maskrcnn_benchmark.trainer INFO: eta: 17:09:00  iter: 300  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6720 (0.6883)  data: 0.0256 (0.0288)  lr: 0.003333  max mem: 7055
2019-04-16 10:37:27,489 maskrcnn_benchmark.trainer INFO: eta: 17:06:42  iter: 320  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6652 (0.6869)  data: 0.0250 (0.0286)  lr: 0.003333  max mem: 7055
2019-04-16 10:37:40,791 maskrcnn_benchmark.trainer INFO: eta: 17:04:34  iter: 340  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6599 (0.6856)  data: 0.0223 (0.0283)  lr: 0.003333  max mem: 7055
2019-04-16 10:37:54,031 maskrcnn_benchmark.trainer INFO: eta: 17:02:22  iter: 360  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6606 (0.6843)  data: 0.0233 (0.0281)  lr: 0.003333  max mem: 7055
2019-04-16 10:38:07,475 maskrcnn_benchmark.trainer INFO: eta: 17:01:12  iter: 380  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6730 (0.6837)  data: 0.0253 (0.0281)  lr: 0.003333  max mem: 7055
2019-04-16 10:38:20,803 maskrcnn_benchmark.trainer INFO: eta: 16:59:40  iter: 400  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6687 (0.6828)  data: 0.0227 (0.0279)  lr: 0.003333  max mem: 7055
2019-04-16 10:38:34,255 maskrcnn_benchmark.trainer INFO: eta: 16:58:43  iter: 420  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6746 (0.6823)  data: 0.0239 (0.0277)  lr: 0.003333  max mem: 7055
2019-04-16 10:38:47,661 maskrcnn_benchmark.trainer INFO: eta: 16:57:40  iter: 440  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6706 (0.6818)  data: 0.0223 (0.0275)  lr: 0.003333  max mem: 7055
2019-04-16 10:39:00,960 maskrcnn_benchmark.trainer INFO: eta: 16:56:21  iter: 460  loss: nan (nan)  loss_cls: nan (nan)  loss_centerness: nan (nan)  loss_reg: nan (nan)  time: 0.6630 (0.6811)  data: 0.0243 (0.0274)  lr: 0.003333  max mem: 7055

I try with python2.7, but loss nan again...

@tianzhi0549
Copy link
Owner

How many times have you tried? If you always encounter NAN, we suggest that you clip the gradients with https://pytorch.org/docs/stable/_modules/torch/nn/utils/clip_grad.html . You can firstly try to set max_norm to 100. If the loss becomes NAN again, please reduce it. Thank you.

@YanShuo1992
Copy link

@tianzhi0549 The python version should not be the cause since I tested the code with python3.7.

@tianzhi0549
Copy link
Owner

@YanShuo1992 OK. Thank you for pointing that out. Maybe some dependencies are different and cause the NAN. Just try to clip gradients. I think it can prevent the loss from exploding.

@bei-startdt
Copy link
Author

hey my friend.
tears on my happy face (ku xiao bu de).
I tried for much times, google and google... but nothing worked..
so my friend say that it maybe one of GPUs error occured.
I checked it and changed GPU selected, and keep config same as repo's origin, it worked.

Thank for your helping!

@tianzhi0549
Copy link
Owner

@bei-startdt Happy to know that you have solved it:-).

@gittigxuy
Copy link

@tianzhi0549,@bei-startdt ,the same problem,how could I deal with the loss nan detaillly?I don't understand how to clip_gradient,I encounter the same issue when I train coco2014 dataset

@tianzhi0549
Copy link
Owner

@gittigxuy Did the loss become NAN many times?

@tianzhi0549
Copy link
Owner

@gittigxuy It should be because your training batch size is only 1. It is too small. We recommend using batch size >= 8.

@gittigxuy
Copy link

Thanks,I have solved the problem,you are right,just config the batch_size>=8

@tianzhi0549 tianzhi0549 mentioned this issue Jun 13, 2019
Closed
@Zeqiang Zeqiang mentioned this issue Oct 15, 2019
Closed
@husthkk
Copy link

husthkk commented Dec 24, 2019

@gittigxuy It should be because your training batch size is only 1. It is too small. We recommend using batch size >= 8.

why does batch size too small cause nan?

@sathyamsn sathyamsn mentioned this issue Sep 17, 2020
Closed
@yonghongl
Copy link

yonghongl commented Jan 6, 2023 •
edited
Loading

@gittigxuy It should be because your training batch size is only 1. It is too small. We recommend using batch size >= 8.

why does batch size too small cause nan?

It's because when calculate sigmoid_focal_loss, torch.log() will output inf result, i.e., torch.log(torch.tensor(1e-49)), then the loss will be nan.

You can modify the following line with p = torch.clamp(torch.sigmoid(logits), min=eps, max= 1 - eps) and make eps as 1e-7, this works for ANY batch size.

FCOS/fcos_core/layers/sigmoid_focal_loss.py

Line 49 in 0eb8ee0

p = torch.sigmoid(logits)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
6 participants
@tianzhi0549 @gittigxuy @husthkk @YanShuo1992 @bei-startdt @yonghongl