Merge pull request #291 from LDOUBLEV/fixeval

set start evaluation
2020-07-07 20:20:54 +08:00 · 2020-07-07 20:20:54 +08:00 · 177d8fd9a5
parent 5067126e8c 5e38ec57a6
commit 177d8fd9a5
9 changed files with 28 additions and 9 deletions
--- a/README.md
+++ b/README.md
@ -92,6 +92,7 @@ python3 tools/infer/predict_system.py --image_dir="./doc/imgs/11.jpg" --det_mode
 - [文本检测模型训练/评估/预测](./doc/doc_ch/detection.md)
 - [文本识别模型训练/评估/预测](./doc/doc_ch/recognition.md)
 - [基于预测引擎推理](./doc/doc_ch/inference.md)
+- [yml配置文件参数介绍](./doc/doc_ch/config_ch.md)
 - [数据集](./doc/doc_ch/datasets.md)
 - [FAQ](#FAQ)
 - [联系我们](#欢迎加入PaddleOCR技术交流群)
--- a/README_en.md
+++ b/README_en.md
@ -92,7 +92,9 @@ For more text detection and recognition models, please refer to the document [In
 - [Text detection model training/evaluation/prediction](./doc/doc_en/detection_en.md)
 - [Text recognition model training/evaluation/prediction](./doc/doc_en/recognition_en.md)
 - [Inference](./doc/doc_en/inference_en.md)
+- [Introduction of yml file](./doc/doc_en/config_en.md)
 - [Dataset](./doc/doc_en/datasets_en.md)
+- [FAQ]((#FAQ)

 ## TEXT DETECTION ALGORITHM

@ -170,6 +172,7 @@ Please refer to the document for training guide and use of PaddleOCR text recogn
 ![](doc/imgs_results/chinese_db_crnn_server/2.jpg)
 ![](doc/imgs_results/chinese_db_crnn_server/8.jpg)

+<a name="FAQ"></a>
 ## FAQ
 1. Error when using attention-based recognition model: KeyError: 'predict'

--- a/configs/det/det_mv3_db.yml
+++ b/configs/det/det_mv3_db.yml
@ -6,7 +6,8 @@ Global:
  print_batch_step: 2
  save_model_dir: ./output/det_db/
  save_epoch_step: 200
-  eval_batch_step: 5000
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 5000]
  train_batch_size_per_card: 16
  test_batch_size_per_card: 16
  image_shape: [3, 640, 640]
@ -50,4 +51,4 @@ PostProcess:
  thresh: 0.3
  box_thresh: 0.7
  max_candidates: 1000
-  unclip_ratio: 2.0
+  unclip_ratio: 2.0
--- a/configs/det/det_mv3_east.yml
+++ b/configs/det/det_mv3_east.yml
@ -6,7 +6,7 @@ Global:
  print_batch_step: 5
  save_model_dir: ./output/det_east/
  save_epoch_step: 200
-  eval_batch_step: 5000
+  eval_batch_step: [5000, 5000]
  train_batch_size_per_card: 16
  test_batch_size_per_card: 16
  image_shape: [3, 512, 512]
--- a/configs/det/det_r50_vd_db.yml
+++ b/configs/det/det_r50_vd_db.yml
@ -6,7 +6,7 @@ Global:
  print_batch_step: 2
  save_model_dir: ./output/det_db/
  save_epoch_step: 200
-  eval_batch_step: 5000
+  eval_batch_step: [5000, 5000]
  train_batch_size_per_card: 8
  test_batch_size_per_card: 16
  image_shape: [3, 640, 640]
--- a/configs/det/det_r50_vd_east.yml
+++ b/configs/det/det_r50_vd_east.yml
@ -6,7 +6,7 @@ Global:
  print_batch_step: 5
  save_model_dir: ./output/det_east/
  save_epoch_step: 200
-  eval_batch_step: 5000
+  eval_batch_step: [5000, 5000]
  train_batch_size_per_card: 8
  test_batch_size_per_card: 16
  image_shape: [3, 512, 512]
--- a/doc/doc_ch/config.md
+++ b/doc/doc_ch/config.md
@ -22,7 +22,7 @@
 |      print_batch_step    |    设置打印log间隔         |       10          |                \                 |
 |      save_model_dir      |    设置模型保存路径        |  output/{算法名称}  |                \                 |
 |      save_epoch_step     |    设置模型保存间隔        |       3           |                \                 |
-|      eval_batch_step     |    设置模型评估间隔        |       2000        |                \                 |
+|      eval_batch_step     |    设置模型评估间隔        | 2000 或 [1000, 2000]        | 2000 表示每2000次迭代评估一次，[1000， 2000]表示从1000次迭代开始，每2000次评估一次   |
 |train_batch_size_per_card |  设置训练时单卡batch size    |         256         |                \                 |
 | test_batch_size_per_card |  设置评估时单卡batch size    |         256         |                \                 |
 |      image_shape         |    设置输入图片尺寸        |   [3, 32, 100]    |                \                 |
--- a/doc/doc_en/config_en.md
+++ b/doc/doc_en/config_en.md
@ -22,7 +22,7 @@ Take `rec_chinese_lite_train.yml` as an example
 |      print_batch_step    |    Set print log interval         |       10          |                \                 |
 |      save_model_dir      |    Set model save path        |  output/{model_name}  |                \                 |
 |      save_epoch_step     |    Set model save interval        |       3           |                \                 |
-|      eval_batch_step     |    Set the model evaluation interval        |       2000        |                \                 |
+|      eval_batch_step     |    Set the model evaluation interval        |2000 or [1000, 2000] |runing evaluation every 2000 iters or evaluation is run every 2000 iterations after the 1000th iteration  |
 |train_batch_size_per_card |  Set the batch size during training   |         256         |                \                 |
 | test_batch_size_per_card |  Set the batch size during testing    |         256         |                \                 |
 |      image_shape         |    Set input image size        |   [3, 32, 100]    |                \                 |
--- a/tools/program.py
+++ b/tools/program.py
@ -219,6 +219,13 @@ def train_eval_det_run(config, exe, train_info_dict, eval_info_dict):
    epoch_num = config['Global']['epoch_num']
    print_batch_step = config['Global']['print_batch_step']
    eval_batch_step = config['Global']['eval_batch_step']
+    start_eval_step = 0
+    if type(eval_batch_step) == list and len(eval_batch_step) >= 2:
+        start_eval_step = eval_batch_step[0]
+        eval_batch_step = eval_batch_step[1]
+        logger.info(
+            "During the training process, after the {}th iteration, an evaluation is run every {} iterations".
+            format(start_eval_step, eval_batch_step))
    save_epoch_step = config['Global']['save_epoch_step']
    save_model_dir = config['Global']['save_model_dir']
    if not os.path.exists(save_model_dir):
@ -246,7 +253,7 @@ def train_eval_det_run(config, exe, train_info_dict, eval_info_dict):
                t2 = time.time()
                train_batch_elapse = t2 - t1
                train_stats.update(stats)
-                if train_batch_id > 0 and train_batch_id \
+                if train_batch_id > start_eval_step and (train_batch_id -start_eval_step)  \
                    % print_batch_step == 0:
                    logs = train_stats.log()
                    strs = 'epoch: {}, iter: {}, {}, time: {:.3f}'.format(
@ -286,6 +293,13 @@ def train_eval_rec_run(config, exe, train_info_dict, eval_info_dict):
    epoch_num = config['Global']['epoch_num']
    print_batch_step = config['Global']['print_batch_step']
    eval_batch_step = config['Global']['eval_batch_step']
+    start_eval_step = 0
+    if type(eval_batch_step) == list and len(eval_batch_step) >= 2:
+        start_eval_step = eval_batch_step[0]
+        eval_batch_step = eval_batch_step[1]
+        logger.info(
+            "During the training process, after the {}th iteration, an evaluation is run every {} iterations".
+            format(start_eval_step, eval_batch_step))
    save_epoch_step = config['Global']['save_epoch_step']
    save_model_dir = config['Global']['save_model_dir']
    if not os.path.exists(save_model_dir):
@ -324,7 +338,7 @@ def train_eval_rec_run(config, exe, train_info_dict, eval_info_dict):
                train_batch_elapse = t2 - t1
                stats = {'loss': loss, 'acc': acc}
                train_stats.update(stats)
-                if train_batch_id > 0 and train_batch_id \
+                if train_batch_id > start_eval_step and (train_batch_id - start_eval_step) \
                    % print_batch_step == 0:
                    logs = train_stats.log()
                    strs = 'epoch: {}, iter: {}, lr: {:.6f}, {}, time: {:.3f}'.format(