add pse config

2e98890d · WenmuZhou · a739abab · 2e98890d · 2e98890d · 2e98890d
4 changed file
--- a/configs/det/det_mv3_pse.yml
+++ b/configs/det/det_mv3_pse.yml
+Global:
+  use_gpu: true
+  epoch_num: 600
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/det_mv3_pse/
+  save_epoch_step: 600
+  # evaluation is run every 63 iterations
+  eval_batch_step: [ 0,63 ]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints: #./output/det_r50_vd_pse_batch8_ColorJitter/best_accuracy
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_pse/predicts_pse.txt
+
+Architecture:
+  model_type: det
+  algorithm: PSE
+  Transform: null
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: FPN
+    out_channels: 96
+  Head:
+    name: PSEHead
+    hidden_dim: 96
+    out_channels: 7
+
+Loss:
+  name: PSELoss
+  alpha: 0.7
+  ohem_ratio: 3
+  kernel_sample_mask: pred
+  reduction: none
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Step
+    learning_rate: 0.001
+    step_size: 200
+    gamma: 0.1
+  regularizer:
+    name: 'L2'
+    factor: 0.0005
+
+PostProcess:
+  name: PSEPostProcess
+  thresh: 0
+  box_thresh: 0.85
+  min_area: 16
+  box_type: box # 'box' or 'poly'
+  scale: 1
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
+    ratio_list: [ 1.0 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - ColorJitter:
+          brightness: 0.12549019607843137
+          saturation: 0.5
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Resize, 'args': { 'size': [ 0.5, 3 ] } }
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [ -10, 10 ] } }
+      - MakePseGt:
+          kernel_num: 7
+          min_shrink_ratio: 0.4
+          size: 640
+      - RandomCropImgMask:
+          size: [ 640,640 ]
+          main_key: gt_text
+          crop_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ]
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [ 0.485, 0.456, 0.406 ]
+          std: [ 0.229, 0.224, 0.225 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 16
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    ratio_list: [ 1.0 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          limit_side_len: 736
+          limit_type: min
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [ 0.485, 0.456, 0.406 ]
+          std: [ 0.229, 0.224, 0.225 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'image', 'shape', 'polys', 'ignore_tags' ]
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 8
\ No newline at end of file
--- a/configs/det/det_r50_vd_pse.yml
+++ b/configs/det/det_r50_vd_pse.yml
@@ -4,16 +4,16 @@ Global:
  log_smooth_window: 20
  print_batch_step: 10
  save_model_dir: ./output/det_r50_vd_pse/
-  save_epoch_step: 1200
-  # evaluation is run every 2000 iterations
-  eval_batch_step: [0,125]
+  save_epoch_step: 600
+  # evaluation is run every 125 iterations
+  eval_batch_step: [ 0,125 ]
  cal_metric_during_train: False
-  pretrained_model: /ssd1/zhoujun20/fuxian/ResNet50_vd_ssld_pretrained
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
  checkpoints: #./output/det_r50_vd_pse_batch8_ColorJitter/best_accuracy
  save_inference_dir:
  use_visualdl: False
  infer_img: doc/imgs_en/img_10.jpg
-  save_res_path: ./output/det_db/predicts_db.txt
+  save_res_path: ./output/det_pse/predicts_pse.txt

 Architecture:
  model_type: det
@@ -68,7 +68,7 @@ Train:
    data_dir: ./train_data/icdar2015/text_localization/
    label_file_list:
      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
-    ratio_list: [1.0]
+    ratio_list: [ 1.0 ]
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
@@ -81,23 +81,23 @@ Train:
          augmenter_args:
            - { 'type': Resize, 'args': { 'size': [ 0.5, 3 ] } }
            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
-            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Affine, 'args': { 'rotate': [ -10, 10 ] } }
      - MakePseGt:
          kernel_num: 7
          min_shrink_ratio: 0.4
          size: 640
      - RandomCropImgMask:
-          size: [640,640]
+          size: [ 640,640 ]
          main_key: gt_text
-          crop_keys: ['image', 'gt_text', 'gt_kernels', 'mask']
+          crop_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ]
      - NormalizeImage:
          scale: 1./255.
-          mean: [0.485, 0.456, 0.406]
-          std: [0.229, 0.224, 0.225]
+          mean: [ 0.485, 0.456, 0.406 ]
+          std: [ 0.229, 0.224, 0.225 ]
          order: 'hwc'
      - ToCHWImage:
      - KeepKeys:
-          keep_keys: ['image', 'gt_text', 'gt_kernels', 'mask'] # the order of the dataloader list
+          keep_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ] # the order of the dataloader list
  loader:
    shuffle: True
    drop_last: False
@@ -119,15 +119,14 @@ Eval:
      - DetResizeForTest:
          limit_side_len: 736
          limit_type: min
-          # resize_long: 2240
      - NormalizeImage:
          scale: 1./255.
-          mean: [0.485, 0.456, 0.406]
-          std: [0.229, 0.224, 0.225]
+          mean: [ 0.485, 0.456, 0.406 ]
+          std: [ 0.229, 0.224, 0.225 ]
          order: 'hwc'
      - ToCHWImage:
      - KeepKeys:
-          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
+          keep_keys: [ 'image', 'shape', 'polys', 'ignore_tags' ]
  loader:
    shuffle: False
    drop_last: False

--- a/doc/doc_ch/algorithm_overview.md
+++ b/doc/doc_ch/algorithm_overview.md
@@ -9,11 +9,13 @@
 ### 1.文本检测算法

 PaddleOCR开源的文本检测算法列表：
- [x]  DB([paper]( https://arxiv.org/abs/1911.08947)) [2]（ppocr推荐）
- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))[1]
- [x]  SAST([paper](https://arxiv.org/abs/1908.05498))[4]
+- [x]  DB([paper]( https://arxiv.org/abs/1911.08947))（ppocr推荐）
+- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))
+- [x]  SAST([paper](https://arxiv.org/abs/1908.05498))
+- [x]  PSENet([paper](https://arxiv.org/abs/1903.12473v2)）

 在ICDAR2015文本检测公开数据集上，算法效果如下：
+
 |模型|骨干网络|precision|recall|Hmean|下载链接|
 | --- | --- | --- | --- | --- | --- |
 |EAST|ResNet50_vd|85.80%|86.71%|86.25%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)|
@@ -21,6 +23,8 @@ PaddleOCR开源的文本检测算法列表：
 |DB|ResNet50_vd|86.41%|78.72%|82.38%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)|
 |DB|MobileNetV3|77.29%|73.08%|75.12%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)|
 |SAST|ResNet50_vd|91.39%|83.77%|87.42%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)|
+|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)|
+|PSE|MobileNetV3|82.20%|70.47%|75.89%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)|

 在Total-text文本检测公开数据集上，算法效果如下：

@@ -39,13 +43,13 @@ PaddleOCR文本检测算法的训练和使用请参考文档教程中[模型训
 ### 2.文本识别算法

 PaddleOCR基于动态图开源的文本识别算法列表：
- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))[7]（ppocr推荐）
- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))[10]
- [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11]
- [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))[12]
- [x]  SRN([paper](https://arxiv.org/abs/2003.12294))[5]
+- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))（ppocr推荐）
+- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))
+- [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))
+- [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))
+- [x]  SRN([paper](https://arxiv.org/abs/2003.12294))

-参考[DTRB][3](https://arxiv.org/abs/1904.01906)文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
+参考[DTRB](https://arxiv.org/abs/1904.01906) 文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：

 |模型|骨干网络|Avg Accuracy|模型存储命名|下载链接|
 |---|---|---|---|---|

--- a/doc/doc_en/algorithm_overview_en.md
+++ b/doc/doc_en/algorithm_overview_en.md
@@ -11,9 +11,10 @@ This tutorial lists the text detection algorithms and text recognition algorithm
 ### 1. Text Detection Algorithm

 PaddleOCR open source text detection algorithms list:
- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))[2]
- [x]  DB([paper](https://arxiv.org/abs/1911.08947))[1]
- [x]  SAST([paper](https://arxiv.org/abs/1908.05498))[4]
+- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))
+- [x]  DB([paper](https://arxiv.org/abs/1911.08947))
+- [x]  SAST([paper](https://arxiv.org/abs/1908.05498))
+- [x]  PSE([paper](https://arxiv.org/abs/1903.12473v2))

 On the ICDAR2015 dataset, the text detection result is as follows:

@@ -24,6 +25,8 @@ On the ICDAR2015 dataset, the text detection result is as follows:
 |DB|ResNet50_vd|86.41%|78.72%|82.38%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)|
 |DB|MobileNetV3|77.29%|73.08%|75.12%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)|
 |SAST|ResNet50_vd|91.39%|83.77%|87.42%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)|
+|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)|
+|PSE|MobileNetV3|82.20%|70.47%|75.89%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)|

 On Total-Text dataset, the text detection result is as follows:

@@ -41,11 +44,11 @@ For the training guide and use of PaddleOCR text detection algorithms, please re
 ### 2. Text Recognition Algorithm

 PaddleOCR open-source text recognition algorithms list:
- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))[7]
- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))[10]
- [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11]
- [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))[12]
- [x]  SRN([paper](https://arxiv.org/abs/2003.12294))[5]
+- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))
+- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))
+- [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))
+- [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))
+- [x]  SRN([paper](https://arxiv.org/abs/2003.12294))

 Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow: