Closed haohao2233 closed 2 years ago
你调用的是评估代码吧,上述信息里没有报错,是正常运行完退出了 你调用的命令是?
Since you haven\'t replied for more than 3 months, we have closed this issue/pr. If the problem is not solved or there is a follow-up one, please reopen it at any time and we will continue to follow up. It is recommended to pull and try the latest code first. 由于您超过三个月未回复,我们将关闭这个issue/pr。 若问题未解决或有后续问题,请随时重新打开(建议先拉取最新代码进行尝试),我们会继续跟进。
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:26: DeprecationWarning:
np.int
is a deprecated alias for the builtinint
. To silence this warning, useint
by itself. Doing this will not modify any behavior and is safe. When replacingnp.int
, you may wish to use e.g.np.int64
ornp.int32
to specify the precision. If you wish to review your current use, check the release note link for additional information. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations def convert_to_list(value, n, name, dtype=np.int): /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/skimage/morphology/skeletonize.py:241: DeprecationWarning:np.bool
is a deprecated alias for the builtinbool
. To silence this warning, usebool
by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.boolhere. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations 0, 1, 1, 0, 0, 1, 0, 0, 0], dtype=np.bool) /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/skimage/morphology/_skeletonize.py:256: DeprecationWarning:
np.boolis a deprecated alias for the builtin
bool. To silence this warning, use
boolby itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use
np.bool_` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations 0, 0, 0, 0, 0, 0, 0, 0, 0], dtype=np.bool) [2021/07/30 09:21:04] root INFO: Architecture : [2021/07/30 09:21:04] root INFO: Backbone : [2021/07/30 09:21:04] root INFO: model_name : large [2021/07/30 09:21:04] root INFO: name : MobileNetV3 [2021/07/30 09:21:04] root INFO: scale : 0.5 [2021/07/30 09:21:04] root INFO: Head : [2021/07/30 09:21:04] root INFO: fc_decay : 0 [2021/07/30 09:21:04] root INFO: name : CTCHead [2021/07/30 09:21:04] root INFO: Neck : [2021/07/30 09:21:04] root INFO: encoder_type : rnn [2021/07/30 09:21:04] root INFO: hidden_size : 96 [2021/07/30 09:21:04] root INFO: name : SequenceEncoder [2021/07/30 09:21:04] root INFO: Transform : None [2021/07/30 09:21:04] root INFO: algorithm : CRNN [2021/07/30 09:21:04] root INFO: model_type : rec [2021/07/30 09:21:04] root INFO: Eval : [2021/07/30 09:21:04] root INFO: dataset : [2021/07/30 09:21:04] root INFO: data_dir : ./train_data/ic15_data [2021/07/30 09:21:04] root INFO: label_file_list : ['./train_data/ic15_data/rec_gt_test.txt'] [2021/07/30 09:21:04] root INFO: name : SimpleDataSet [2021/07/30 09:21:04] root INFO: transforms : [2021/07/30 09:21:04] root INFO: DecodeImage : [2021/07/30 09:21:04] root INFO: channel_first : False [2021/07/30 09:21:04] root INFO: img_mode : BGR [2021/07/30 09:21:04] root INFO: CTCLabelEncode : None [2021/07/30 09:21:04] root INFO: RecResizeImg : [2021/07/30 09:21:04] root INFO: image_shape : [3, 32, 100] [2021/07/30 09:21:04] root INFO: KeepKeys : [2021/07/30 09:21:04] root INFO: keep_keys : ['image', 'label', 'length'] [2021/07/30 09:21:04] root INFO: loader : [2021/07/30 09:21:04] root INFO: batch_size_per_card : 2 [2021/07/30 09:21:04] root INFO: drop_last : False [2021/07/30 09:21:04] root INFO: num_workers : 2 [2021/07/30 09:21:04] root INFO: shuffle : False [2021/07/30 09:21:04] root INFO: use_shared_memory : False [2021/07/30 09:21:04] root INFO: Global : [2021/07/30 09:21:04] root INFO: cal_metric_during_train : True [2021/07/30 09:21:04] root INFO: character_dict_path : ppocr/utils/ic15_dict.txt [2021/07/30 09:21:04] root INFO: character_type : ch [2021/07/30 09:21:04] root INFO: checkpoints : None [2021/07/30 09:21:04] root INFO: debug : False [2021/07/30 09:21:04] root INFO: distributed : False [2021/07/30 09:21:04] root INFO: epoch_num : 40 [2021/07/30 09:21:04] root INFO: eval_batch_step : [0, 10] [2021/07/30 09:21:04] root INFO: infer_img : doc/imgs_words_en/word_10.png [2021/07/30 09:21:04] root INFO: infer_mode : False [2021/07/30 09:21:04] root INFO: log_smooth_window : 20 [2021/07/30 09:21:04] root INFO: max_text_length : 25 [2021/07/30 09:21:04] root INFO: pretrained_model : ./pretrain_models/rec_mv3_none_bilstm_ctc_v2.0_train/best_accuracy [2021/07/30 09:21:04] root INFO: print_batch_step : 10 [2021/07/30 09:21:04] root INFO: save_epoch_step : 5 [2021/07/30 09:21:04] root INFO: save_inference_dir : None [2021/07/30 09:21:04] root INFO: save_model_dir : ./output/rec/ic15/ [2021/07/30 09:21:04] root INFO: use_gpu : True [2021/07/30 09:21:04] root INFO: use_space_char : False [2021/07/30 09:21:04] root INFO: use_visualdl : False [2021/07/30 09:21:04] root INFO: Loss : [2021/07/30 09:21:04] root INFO: name : CTCLoss [2021/07/30 09:21:04] root INFO: Metric : [2021/07/30 09:21:04] root INFO: main_indicator : acc [2021/07/30 09:21:04] root INFO: name : RecMetric [2021/07/30 09:21:04] root INFO: Optimizer : [2021/07/30 09:21:04] root INFO: beta1 : 0.9 [2021/07/30 09:21:04] root INFO: beta2 : 0.999 [2021/07/30 09:21:04] root INFO: lr : [2021/07/30 09:21:04] root INFO: learning_rate : 0.0001 [2021/07/30 09:21:04] root INFO: name : Adam [2021/07/30 09:21:04] root INFO: regularizer : [2021/07/30 09:21:04] root INFO: factor : 0 [2021/07/30 09:21:04] root INFO: name : L2 [2021/07/30 09:21:04] root INFO: PostProcess : [2021/07/30 09:21:04] root INFO: name : CTCLabelDecode [2021/07/30 09:21:04] root INFO: Train : [2021/07/30 09:21:04] root INFO: dataset : [2021/07/30 09:21:04] root INFO: data_dir : ./train_data/ic15_data [2021/07/30 09:21:04] root INFO: label_file_list : ['./train_data/ic15_data/rec_gt_train.txt'] [2021/07/30 09:21:04] root INFO: name : SimpleDataSet [2021/07/30 09:21:04] root INFO: transforms : [2021/07/30 09:21:04] root INFO: DecodeImage : [2021/07/30 09:21:04] root INFO: channel_first : False [2021/07/30 09:21:04] root INFO: img_mode : BGR [2021/07/30 09:21:04] root INFO: CTCLabelEncode : None [2021/07/30 09:21:04] root INFO: RecResizeImg : [2021/07/30 09:21:04] root INFO: image_shape : [3, 32, 100] [2021/07/30 09:21:04] root INFO: KeepKeys : [2021/07/30 09:21:04] root INFO: keep_keys : ['image', 'label', 'length'] [2021/07/30 09:21:04] root INFO: loader : [2021/07/30 09:21:04] root INFO: batch_size_per_card : 2 [2021/07/30 09:21:04] root INFO: drop_last : True [2021/07/30 09:21:04] root INFO: num_workers : 2 [2021/07/30 09:21:04] root INFO: shuffle : True [2021/07/30 09:21:04] root INFO: use_shared_memory : False [2021/07/30 09:21:04] root INFO: train with paddle 2.0.2 and device CUDAPlace(0) [2021/07/30 09:21:04] root INFO: Initialize indexs of datasets:['./train_data/ic15_data/rec_gt_test.txt'] W0730 09:21:04.186337 2350 device_context.cc:362] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1 W0730 09:21:04.191743 2350 device_context.cc:372] device: 0, cuDNN Version: 7.6. [2021/07/30 09:21:09] root INFO: load pretrained model from ['./pretrain_models/rec_mv3_none_bilstm_ctc_v2.0_train/best_accuracy'] eval model:: 100%|██████████████████████████| 1039/1039 [00:23<00:00, 43.99it/s] [2021/07/30 09:21:32] root INFO: metric eval *** [2021/07/30 09:21:32] root INFO: acc:0.2532498796340876 [2021/07/30 09:21:32] root INFO: norm_edit_dis:0.7086016893146361 [2021/07/30 09:21:32] root INFO: fps:90.20009442693762