first commit

configs/det/det_r50_vd_sast_totaltext.yml

@@ -0,0 +1,108 @@
+Global:
+  use_gpu: true
+  epoch_num: 5000
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/sast_r50_vd_tt/
+  save_epoch_step: 1000
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 5000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: 
+  save_res_path: ./output/sast_r50_vd_tt/predicts_sast.txt
+
+Architecture:
+  model_type: det
+  algorithm: SAST
+  Transform:
+  Backbone:
+    name: ResNet_SAST
+    layers: 50
+  Neck:
+    name: SASTFPN
+    with_cab: True
+  Head:
+    name: SASTHead
+
+Loss:
+  name: SASTLoss
+  
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+  #  name: Cosine
+    learning_rate: 0.001
+  #  warmup_epoch: 0
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: SASTPostProcess
+  score_thresh: 0.5
+  sample_pts_num: 6
+  nms_thresh: 0.2
+  expand_scale: 1.2
+  shrink_ratio_of_width: 0.2
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: [./train_data/art_latin_icdar_14pt/train_no_tt_test/train_label_json.txt, ./train_data/total_text_icdar_14pt/train_label_json.txt]
+    ratio_list: [0.5, 0.5]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - SASTProcessTrain:
+          image_shape: [512, 512]
+          min_crop_side_ratio: 0.3
+          min_crop_size: 24
+          min_text_size: 4
+          max_text_size: 512
+      - KeepKeys:
+          keep_keys: ['image', 'score_map', 'border_map', 'training_mask', 'tvo_map', 'tco_map'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 4
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: 
+        - ./train_data/total_text_icdar_14pt/test_label_json.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          resize_long: 768
+      - 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