first commit

configs/det/det_r50_drrg_ctw.yml

@@ -0,0 +1,133 @@
+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 5
+  save_model_dir: ./output/det_r50_drrg_ctw/
+  save_epoch_step: 100
+  # evaluation is run every 1260 iterations
+  eval_batch_step: [37800, 1260]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained.pdparams 
+  checkpoints: 
+  save_inference_dir: 
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_drrg/predicts_drrg.txt
+
+
+Architecture:
+  model_type: det
+  algorithm: DRRG
+  Transform:
+  Backbone:
+    name: ResNet_vd
+    layers: 50
+  Neck:
+    name: FPN_UNet
+    in_channels: [256, 512, 1024, 2048]
+    out_channels: 32
+  Head:
+    name: DRRGHead
+    in_channels: 32
+    text_region_thr: 0.3
+    center_region_thr: 0.4
+Loss:
+  name: DRRGLoss
+  
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: DecayLearningRate
+    learning_rate: 0.028
+    epochs: 1200
+    factor: 0.9
+    end_lr: 0.0000001
+  weight_decay: 0.0001
+
+PostProcess:
+  name: DRRGPostprocess
+  link_thr: 0.8
+
+Metric:
+  name: DetFCEMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ctw1500/imgs/
+    label_file_list: 
+      - ./train_data/ctw1500/imgs/training.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+          ignore_orientation: True
+      - DetLabelEncode: # Class handling label
+      - ColorJitter: 
+          brightness: 0.12549019607843137
+          saturation: 0.5
+      - RandomScaling: 
+      - RandomCropFlip:
+          crop_ratio: 0.5
+      - RandomCropPolyInstances:
+          crop_ratio: 0.8
+          min_side_ratio: 0.3
+      - RandomRotatePolyInstances:
+          rotate_ratio: 0.5
+          max_angle: 60
+          pad_with_fixed_color: False
+      - SquareResizePad:
+          target_size: 800
+          pad_ratio: 0.6
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+      - DRRGTargets:
+      - 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_mask', 'gt_center_region_mask', 'gt_mask',
+            'gt_top_height_map', 'gt_bot_height_map', 'gt_sin_map',
+            'gt_cos_map', 'gt_comp_attribs'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 4
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ctw1500/imgs/
+    label_file_list:
+      - ./train_data/ctw1500/imgs/test.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+          ignore_orientation: True
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          limit_type: 'min'
+          limit_side_len: 640
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - Pad: 
+      - 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