RuntimeError: Not implemented on the CPU

[MorningBanana]

when I'm trying to run the file trainval_net, it returns an error: "RuntimeError: Not implemented on the CPU (ROIAlign_backward at /home/qxf/Documents/faster-rcnn.pytorch-pytorch-1.0/lib/model/csrc/ROIAlign.h:44)", what can I do to deal with this? Thanks a lot!

The whole outputs are as follow:
Loading pretrained weights from data/pretrained_model/resnet101_caffe.pth
Traceback (most recent call last):
File "/home/qxf/Documents/faster-rcnn.pytorch-pytorch-1.0/trainval_net.py", line 329, in
loss.backward()
File "/home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/tensor.py", line 102, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/autograd/init.py", line 90, in backward
allow_unreachable=True) # allow_unreachable flag
File "/home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/autograd/function.py", line 76, in apply
return self._forward_cls.backward(self, *args)
File "/home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/autograd/function.py", line 188, in wrapper
outputs = fn(ctx, args)
File "/home/qxf/Documents/faster-rcnn.pytorch-pytorch-1.0/lib/model/roi_layers/roi_align.py", line 41, in backward
sampling_ratio,
RuntimeError: Not implemented on the CPU (ROIAlign_backward at /home/qxf/Documents/faster-rcnn.pytorch-pytorch-1.0/lib/model/csrc/ROIAlign.h:44)
frame #0: std::function<std::string ()>::operator()() const + 0x11 (0x7f2000662fe1 in /home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/lib/libc10.so)
frame #1: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x2a (0x7f2000662dfa in /home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/lib/libc10.so)
frame #2: ROIAlign_backward(at::Tensor const&, at::Tensor const&, float, int, int, int, int, int, int, int) + 0xfe (0x7f20543016ae in /home/qxf/Documents/faster-rcnn.pytorch-pytorch-1.0/lib/model/_C.so)
frame #3: + 0x1657f (0x7f205430e57f in /home/qxf/Documents/faster-rcnn.pytorch-pytorch-1.0/lib/model/_C.so)
frame #4: + 0x1667e (0x7f205430e67e in /home/qxf/Documents/faster-rcnn.pytorch-pytorch-1.0/lib/model/_C.so)
frame #5: + 0x12b32 (0x7f205430ab32 in /home/qxf/Documents/faster-rcnn.pytorch-pytorch-1.0/lib/model/_C.so)
frame #6: PyEval_EvalFrameEx + 0x5ca (0x4bc4aa in /home/qxf/PT1.0/bin/python)
frame #7: PyEval_EvalCodeEx + 0x306 (0x4b9b66 in /home/qxf/PT1.0/bin/python)
frame #8: /home/qxf/PT1.0/bin/python() [0x4d5669]
frame #9: PyObject_Call + 0x3e (0x4a587e in /home/qxf/PT1.0/bin/python)
frame #10: PyEval_EvalFrameEx + 0x263e (0x4be51e in /home/qxf/PT1.0/bin/python)
frame #11: PyEval_EvalCodeEx + 0x306 (0x4b9b66 in /home/qxf/PT1.0/bin/python)
frame #12: /home/qxf/PT1.0/bin/python() [0x4d5669]
frame #13: PyObject_Call + 0x3e (0x4a587e in /home/qxf/PT1.0/bin/python)
frame #14: PyEval_EvalFrameEx + 0x263e (0x4be51e in /home/qxf/PT1.0/bin/python)
frame #15: PyEval_EvalCodeEx + 0x306 (0x4b9b66 in /home/qxf/PT1.0/bin/python)
frame #16: /home/qxf/PT1.0/bin/python() [0x4d5669]
frame #17: /home/qxf/PT1.0/bin/python() [0x4eef5e]
frame #18: PyObject_Call + 0x3e (0x4a587e in /home/qxf/PT1.0/bin/python)
frame #19: PyEval_CallObjectWithKeywords + 0x30 (0x4c5ef0 in /home/qxf/PT1.0/bin/python)
frame #20: torch::autograd::PyFunction::apply(std::vector<torch::autograd::Variable, std::allocatortorch::autograd::Variable >&&) + 0x193 (0x7f203a992883 in /home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/lib/libtorch_python.so)
frame #21: torch::autograd::Engine::evaluate_function(torch::autograd::FunctionTask&) + 0x39e (0x7f1ffeff941e in /home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/lib/libtorch.so.1)
frame #22: torch::autograd::Engine::thread_main(torch::autograd::GraphTask) + 0xc0 (0x7f1ffeffb580 in /home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/lib/libtorch.so.1)
frame #23: torch::autograd::Engine::thread_init(int) + 0xc7 (0x7f1ffeff7e57 in /home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/lib/libtorch.so.1)
frame #24: torch::autograd::python::PythonEngine::thread_init(int) + 0x2a (0x7f203a98d31a in /home/qxf/PT1.0/local/lib/python2.7/site-packages/torch/lib/libtorch_python.so)
frame #25: + 0xb8c80 (0x7f204f44ac80 in /usr/lib/x86_64-linux-gnu/libstdc++.so.6)
frame #26: + 0x76ba (0x7f2053fc06ba in /lib/x86_64-linux-gnu/libpthread.so.0)
frame #27: clone + 0x6d (0x7f2053cf641d in /lib/x86_64-linux-gnu/libc.so.6)

[sectionzzz]

Just run with CUDA simply then it solves:
python trainval_net.py --cuda

[lpc777]

it works, thank you very much

[VeenaUpendran]

File "C:\Veena\faster-rcnn.pytorch\lib\model\roi_layers\roi_align.py", line 41, in backward
sampling_ratio,
RuntimeError: Not implemented on the CPU

I am facing this issue

[VeenaUpendran]

$ python trainval_net.py
Called with args:
Namespace(batch_size=1, checkepoch=1, checkpoint=0, checkpoint_interval=10000, checksession=1, class_agnostic=False, cuda=False, dataset='pascal_voc', disp_interval=100, large_scale=False, lr=0.001, lr_decay_gamma=0.1, lr_decay_step=5, mGPUs=False, max_epochs=20, net='vgg16', num_workers=0, optimizer='sgd', resume=False, save_dir='models', session=1, start_epoch=1, use_tfboard=False)
C:\Veena\faster-rcnn.pytorch\lib\model\utils\config.py:374: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
yaml_cfg = edict(yaml.load(f))
Using config:
{'ANCHOR_RATIOS': [0.5, 1, 2],
'ANCHOR_SCALES': [8, 16, 32],
'CROP_RESIZE_WITH_MAX_POOL': False,
'CUDA': False,
'DATA_DIR': 'C:\Veena\faster-rcnn.pytorch\data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'vgg16',
'FEAT_STRIDE': [16],
'GPU_ID': 0,
'MATLAB': 'matlab',
'MAX_NUM_GT_BOXES': 20,
'MOBILENET': {'DEPTH_MULTIPLIER': 1.0,
'FIXED_LAYERS': 5,
'REGU_DEPTH': False,
'WEIGHT_DECAY': 4e-05},
'PIXEL_MEANS': array([[[102.9801, 115.9465, 122.7717]]]),
'POOLING_MODE': 'align',
'POOLING_SIZE': 7,
'RESNET': {'FIXED_BLOCKS': 1, 'MAX_POOL': False},
'RNG_SEED': 3,
'ROOT_DIR': 'C:\Veena\faster-rcnn.pytorch',
'TEST': {'BBOX_REG': True,
'HAS_RPN': True,
'MAX_SIZE': 1000,
'MODE': 'nms',
'NMS': 0.3,
'PROPOSAL_METHOD': 'gt',
'RPN_MIN_SIZE': 16,
'RPN_NMS_THRESH': 0.7,
'RPN_POST_NMS_TOP_N': 300,
'RPN_PRE_NMS_TOP_N': 6000,
'RPN_TOP_N': 5000,
'SCALES': [600],
'SVM': False},
'TRAIN': {'ASPECT_GROUPING': False,
'BATCH_SIZE': 256,
'BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'BBOX_NORMALIZE_MEANS': [0.0, 0.0, 0.0, 0.0],
'BBOX_NORMALIZE_STDS': [0.1, 0.1, 0.2, 0.2],
'BBOX_NORMALIZE_TARGETS': True,
'BBOX_NORMALIZE_TARGETS_PRECOMPUTED': True,
'BBOX_REG': True,
'BBOX_THRESH': 0.5,
'BG_THRESH_HI': 0.5,
'BG_THRESH_LO': 0.0,
'BIAS_DECAY': False,
'BN_TRAIN': False,
'DISPLAY': 10,
'DOUBLE_BIAS': True,
'FG_FRACTION': 0.25,
'FG_THRESH': 0.5,
'GAMMA': 0.1,
'HAS_RPN': True,
'IMS_PER_BATCH': 1,
'LEARNING_RATE': 0.01,
'MAX_SIZE': 1000,
'MOMENTUM': 0.9,
'PROPOSAL_METHOD': 'gt',
'RPN_BATCHSIZE': 256,
'RPN_BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'RPN_CLOBBER_POSITIVES': False,
'RPN_FG_FRACTION': 0.5,
'RPN_MIN_SIZE': 8,
'RPN_NEGATIVE_OVERLAP': 0.3,
'RPN_NMS_THRESH': 0.7,
'RPN_POSITIVE_OVERLAP': 0.7,
'RPN_POSITIVE_WEIGHT': -1.0,
'RPN_POST_NMS_TOP_N': 2000,
'RPN_PRE_NMS_TOP_N': 12000,
'SCALES': [600],
'SNAPSHOT_ITERS': 5000,
'SNAPSHOT_KEPT': 3,
'SNAPSHOT_PREFIX': 'res101_faster_rcnn',
'STEPSIZE': [30000],
'SUMMARY_INTERVAL': 180,
'TRIM_HEIGHT': 600,
'TRIM_WIDTH': 600,
'TRUNCATED': False,
'USE_ALL_GT': True,
'USE_FLIPPED': True,
'USE_GT': False,
'WEIGHT_DECAY': 0.0005},
'USE_GPU_NMS': True}
Loaded dataset voc_2007_trainval for training
Set proposal method: gt
Appending horizontally-flipped training examples...
voc_2007_trainval gt roidb loaded from C:\Veena\faster-rcnn.pytorch\data\cache\voc_2007_trainval_gt_roidb.pkl
done
Preparing training data...
done
before filtering, there are 10022 images...
after filtering, there are 10022 images...
10022 roidb entries
Loading pretrained weights from data/pretrained_model/vgg16_caffe.pth
Traceback (most recent call last):
File "trainval_net.py", line 329, in
loss.backward()
File "C:\Users\arjun\AppData\Local\Programs\Python\Python37\lib\site-packages\torch_tensor.py", line 489, in backward
self, gradient, retain_graph, create_graph, inputs=inputs
File "C:\Users\arjun\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\autograd_init_.py", line 199, in backward
allow_unreachable=True, accumulate_grad=True) # Calls into the C++ engine to run the backward pass
File "C:\Users\arjun\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\autograd\function.py", line 267, in apply
return user_fn(self, *args)
File "C:\Users\arjun\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\autograd\function.py", line 414, in wrapper
outputs = fn(ctx, *args)
File "C:\Veena\faster-rcnn.pytorch\lib\model\roi_layers\roi_align.py", line 41, in backward
sampling_ratio,
RuntimeError: Not implemented on the CPU

arjun@LAPTOP-B7JENB0H MINGW64 /c/Veena/faster-rcnn.pytorch (pytorch-1.0)
$ python trainval_net.py
Called with args:
Namespace(batch_size=1, checkepoch=1, checkpoint=0, checkpoint_interval=10000, checksession=1, class_agnostic=False, cuda=False, dataset='pascal_voc', disp_interval=100, large_scale=False, lr=0.001, lr_decay_gamma=0.1, lr_decay_step=5, mGPUs=False, max_epochs=20, net='vgg16', num_workers=0, optimizer='sgd', resume=False, save_dir='models', session=1, start_epoch=1, use_tfboard=False)
C:\Veena\faster-rcnn.pytorch\lib\model\utils\config.py:374: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
yaml_cfg = edict(yaml.load(f))
Using config:
{'ANCHOR_RATIOS': [0.5, 1, 2],
'ANCHOR_SCALES': [8, 16, 32],
'CROP_RESIZE_WITH_MAX_POOL': False,
'CUDA': False,
'DATA_DIR': 'C:\Veena\faster-rcnn.pytorch\data',
'DEDUP_BOXES': 0.0625,
'EPS': 1e-14,
'EXP_DIR': 'vgg16',
'FEAT_STRIDE': [16],
'GPU_ID': 0,
'MATLAB': 'matlab',
'MAX_NUM_GT_BOXES': 20,
'MOBILENET': {'DEPTH_MULTIPLIER': 1.0,
'FIXED_LAYERS': 5,
'REGU_DEPTH': False,
'WEIGHT_DECAY': 4e-05},
'PIXEL_MEANS': array([[[102.9801, 115.9465, 122.7717]]]),
'POOLING_MODE': 'align',
'POOLING_SIZE': 7,
'RESNET': {'FIXED_BLOCKS': 1, 'MAX_POOL': False},
'RNG_SEED': 3,
'ROOT_DIR': 'C:\Veena\faster-rcnn.pytorch',
'TEST': {'BBOX_REG': True,
'HAS_RPN': True,
'MAX_SIZE': 1000,
'MODE': 'nms',
'NMS': 0.3,
'PROPOSAL_METHOD': 'gt',
'RPN_MIN_SIZE': 16,
'RPN_NMS_THRESH': 0.7,
'RPN_POST_NMS_TOP_N': 300,
'RPN_PRE_NMS_TOP_N': 6000,
'RPN_TOP_N': 5000,
'SCALES': [600],
'SVM': False},
'TRAIN': {'ASPECT_GROUPING': False,
'BATCH_SIZE': 256,
'BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'BBOX_NORMALIZE_MEANS': [0.0, 0.0, 0.0, 0.0],
'BBOX_NORMALIZE_STDS': [0.1, 0.1, 0.2, 0.2],
'BBOX_NORMALIZE_TARGETS': True,
'BBOX_NORMALIZE_TARGETS_PRECOMPUTED': True,
'BBOX_REG': True,
'BBOX_THRESH': 0.5,
'BG_THRESH_HI': 0.5,
'BG_THRESH_LO': 0.0,
'BIAS_DECAY': False,
'BN_TRAIN': False,
'DISPLAY': 10,
'DOUBLE_BIAS': True,
'FG_FRACTION': 0.25,
'FG_THRESH': 0.5,
'GAMMA': 0.1,
'HAS_RPN': True,
'IMS_PER_BATCH': 1,
'LEARNING_RATE': 0.01,
'MAX_SIZE': 1000,
'MOMENTUM': 0.9,
'PROPOSAL_METHOD': 'gt',
'RPN_BATCHSIZE': 256,
'RPN_BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'RPN_CLOBBER_POSITIVES': False,
'RPN_FG_FRACTION': 0.5,
'RPN_MIN_SIZE': 8,
'RPN_NEGATIVE_OVERLAP': 0.3,
'RPN_NMS_THRESH': 0.7,
'RPN_POSITIVE_OVERLAP': 0.7,
'RPN_POSITIVE_WEIGHT': -1.0,
'RPN_POST_NMS_TOP_N': 2000,
'RPN_PRE_NMS_TOP_N': 12000,
'SCALES': [600],
'SNAPSHOT_ITERS': 5000,
'SNAPSHOT_KEPT': 3,
'SNAPSHOT_PREFIX': 'res101_faster_rcnn',
'STEPSIZE': [30000],
'SUMMARY_INTERVAL': 180,
'TRIM_HEIGHT': 600,
'TRIM_WIDTH': 600,
'TRUNCATED': False,
'USE_ALL_GT': True,
'USE_FLIPPED': True,
'USE_GT': False,
'WEIGHT_DECAY': 0.0005},
'USE_GPU_NMS': True}
Loaded dataset voc_2007_trainval for training
Set proposal method: gt
Appending horizontally-flipped training examples...
voc_2007_trainval gt roidb loaded from C:\Veena\faster-rcnn.pytorch\data\cache\voc_2007_trainval_gt_roidb.pkl
done
Preparing training data...
done
before filtering, there are 10022 images...
after filtering, there are 10022 images...
10022 roidb entries
Loading pretrained weights from data/pretrained_model/vgg16_caffe.pth
Traceback (most recent call last):
File "trainval_net.py", line 329, in
loss.backward()
File "C:\Users\arjun\AppData\Local\Programs\Python\Python37\lib\site-packages\torch_tensor.py", line 489, in backward
self, gradient, retain_graph, create_graph, inputs=inputs
File "C:\Users\arjun\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\autograd_init_.py", line 199, in backward
allow_unreachable=True, accumulate_grad=True) # Calls into the C++ engine to run the backward pass
File "C:\Users\arjun\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\autograd\function.py", line 267, in apply
return user_fn(self, *args)
File "C:\Users\arjun\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\autograd\function.py", line 414, in wrapper
outputs = fn(ctx, *args)
File "C:\Veena\faster-rcnn.pytorch\lib\model\roi_layers\roi_align.py", line 41, in backward
sampling_ratio,
RuntimeError: Not implemented on the CPU

please help

[xiaojunjun65]

WO YE YUUDAO LE