ocr训练(检测+识别)，best_accuracy模型都没有生成的问题

[zyj0721]

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

• 系统环境/System Environment：windows
• 版本号/Version：Paddle：2.5.2 PaddleOCR：2.7.0.3
• 运行指令/Command Code：python tools/train.py -c configs/rec/PP-OCRv3/ch_PP-OCRv3_rec.yml
• 完整报错/Complete Error Message：没有报错

`Global:
debug: false
use_gpu: false
epoch_num: 10
log_smooth_window: 2
print_batch_step: 1
save_model_dir: ./output/rec_ppocr_v3
save_epoch_step: 3
eval_batch_step: [0, 2]
cal_metric_during_train: true
pretrained_model: ./pretrain_models/ch_ppocr_server_v2.0_rec_train/best_accuracy.pdparams
checkpoints:
save_inference_dir:
use_visualdl: false
infer_img: doc/imgs_words/ch/word_1.jpg
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
max_text_length: &max_text_length 250
infer_mode: false
use_space_char: true
distributed: true
save_res_path: ./output/rec/predicts_ppocrv3.txt

Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 5
regularizer:
name: L2
factor: 3.0e-05

Architecture:
model_type: rec
algorithm: SVTR_LCNet
Transform:
Backbone:
name: MobileNetV1Enhance
scale: 0.5
last_conv_stride: [1, 2]
last_pool_type: avg
last_pool_kernel_size: [2, 2]
Head:
name: MultiHead
head_list:
- CTCHead:
Neck:
name: svtr
dims: 64
depth: 2
hidden_dims: 120
use_guide: True
Head:
fc_decay: 0.00001
- SARHead:
enc_dim: 512
max_text_length: *max_text_length

Loss:
name: MultiLoss
loss_config_list:
- CTCLoss:
- SARLoss:

PostProcess:
name: CTCLabelDecode

Metric:
name: RecMetric
main_indicator: acc
ignore_space: False

Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
ext_op_transform_idx: 1
label_file_list:
- ./train_data/rec/train.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecConAug:
prob: 0.5
ext_data_num: 2
image_shape: [48, 320, 3]
max_text_length: *max_text_length
- RecAug:
- MultiLabelEncode:
- RecResizeImg:
image_shape: [3, 48, 320]
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_sar
- length
- valid_ratio
loader:
shuffle: true
batch_size_per_card: 128
drop_last: true
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data
label_file_list:
- ./train_data/rec/val.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- MultiLabelEncode:
- RecResizeImg:
image_shape: [3, 48, 320]
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_sar
- length
- valid_ratio
loader:
shuffle: false
drop_last: false
batch_size_per_card: 128
num_workers: 4
`

能够正常生成iter_epoch_n.文件，但是一直没有best_accuracy.，请问这是什么原因呢？

[xiongwujun]

同问

[laokamo]

我也遇到这样的问题

• 系统环境/System Environment：windows
• 版本号/Version：PaddleOCR-release-2.6.1
• 运行指令/Command Code：python tools/train.py -c configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_danju.yml
• 完整报错/Complete Error Message：没有报错

Global:
debug: true
use_gpu: true
epoch_num: &epoch_num 2400
log_smooth_window: 20
print_batch_step: 100
save_model_dir: ./output/ch_PP-OCRv4
save_epoch_step: 100
eval_batch_step:

• 0
• 100
  cal_metric_during_train: false
  checkpoints:
  pretrained_model: ./pretrain_models/ch_PP-OCRv4_det_server_train/best_accuracy.pdparams
  save_inference_dir: null
  use_visualdl: false
  infer_img: doc/imgs_en/img_10.jpg
  save_res_path: ./checkpoints/det_db/predicts_db.txt
  distributed: true

Architecture:
model_type: det
algorithm: DB
Transform: null
Backbone:
name: PPHGNet_small
det: True
Neck:
name: LKPAN
out_channels: 256
intracl: true
Head:
name: PFHeadLocal
k: 50
mode: "large"

Loss:
name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3

Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.01 #(8*8c)
warmup_epoch: 2
regularizer:
name: L2
factor: 1e-6

PostProcess:
name: DBPostProcess
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5

Metric:
name: DetMetric
main_indicator: hmean

Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list:
- ./train_data/det/train.txt
ratio_list: [1.0]
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- DetLabelEncode: null
- CopyPaste: null
- IaaAugment:
augmenter_args:
- type: Fliplr
args:
p: 0.5
- type: Affine
args:
rotate:
- -10
- 10
- type: Resize
args:
size:
- 0.5
- 3
- EastRandomCropData:
size:
- 640
- 640
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
total_epoch: *epoch_num
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
total_epoch: *epoch_num
- NormalizeImage:
scale: 1./255.
mean:
- 0.485
- 0.456
- 0.406
std:
- 0.229
- 0.224
- 0.225
order: hwc
- ToCHWImage: null
- KeepKeys:
keep_keys:
- image
- threshold_map
- threshold_mask
- shrink_map
- shrink_mask
loader:
shuffle: true
drop_last: false
batch_size_per_card: 8
num_workers: 8

Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list:
- ./train_data/det/val.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- DetLabelEncode: null
- DetResizeForTest:
- NormalizeImage:
scale: 1./255.
mean:
- 0.485
- 0.456
- 0.406
std:
- 0.229
- 0.224
- 0.225
order: hwc
- ToCHWImage: null
- KeepKeys:
keep_keys:
- image
- shape
- polys
- ignore_tags
loader:
shuffle: false
drop_last: false
batch_size_per_card: 1
num_workers: 2
profiler_options: null

[aqingGitHub]

你好！解决了吗，我也遇到同样的问题

[UserWangZz]

检查一下log文件中eval时的性能？如果没有提升是不会保存best model的

[aqingGitHub]

和训练的图片张数是否有关，一般要多少张呢？

[UserWangZz]

检测1000张以上，识别5000以上