From eb4a29e38146af91e27b8ce938c0bd866447868e Mon Sep 17 00:00:00 2001
From: LDOUBLEV <liuvv0203@outlook.com>
Date: Fri, 3 Sep 2021 10:40:06 +0000
Subject: [PATCH] fix config about det distill

---
 .../ch_det_lite_train_cml_v2.1.yml            |   5 +-
 .../ch_det_mv3_db_v2.1_student.yml            | 132 ++++++++++++++++++
 2 files changed, 133 insertions(+), 4 deletions(-)
 create mode 100644 configs/det/ch_ppocr_v2.1/ch_det_mv3_db_v2.1_student.yml

diff --git a/configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml b/configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml
index dcf0e1f2..9bcabbe7 100644
--- a/configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml
+++ b/configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml
@@ -8,7 +8,7 @@ Global:
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [3000, 2000]
   cal_metric_during_train: False
-  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+  pretrained_model: ./pretrain_models/ch_ppocr_mobile_v2.1_det_distill_train/best_accuracy
   checkpoints:
   save_inference_dir:
   use_visualdl: False
@@ -20,7 +20,6 @@ Architecture:
   algorithm: Distillation
   Models:
     Student:
-      pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
       freeze_params: false
       return_all_feats: false
       model_type: det
@@ -37,7 +36,6 @@ Architecture:
         name: DBHead
         k: 50
     Student2:
-      pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
       freeze_params: false
       return_all_feats: false
       model_type: det
@@ -55,7 +53,6 @@ Architecture:
         name: DBHead
         k: 50
     Teacher:
-      pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
       freeze_params: true
       return_all_feats: false
       model_type: det
diff --git a/configs/det/ch_ppocr_v2.1/ch_det_mv3_db_v2.1_student.yml b/configs/det/ch_ppocr_v2.1/ch_det_mv3_db_v2.1_student.yml
new file mode 100644
index 00000000..cca2a596
--- /dev/null
+++ b/configs/det/ch_ppocr_v2.1/ch_det_mv3_db_v2.1_student.yml
@@ -0,0 +1,132 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/ch_db_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 400]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/student.pdparams
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: DBFPN
+    out_channels: 96
+  Head:
+    name: DBHead
+    k: 50
+
+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: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+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/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
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - 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', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+#           image_shape: [736, 1280]
+      - 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: 2
-- 
GitLab