mindspore-lab · tonytonglt · Jan 29, 2024 · Jan 29, 2024
diff --git a/configs/det/dbnet/README_CN.md b/configs/det/dbnet/README_CN.md
@@ -66,16 +66,17 @@ DBNet和DBNet++在ICDAR2015，MSRA-TD500，SCUT-CTW1500，Total-Text和MLT2017
 ### ICDAR2015
 <div align="center">
 
-| **模型**              | **环境配置**       | **骨干网络**      | **预训练数据集** | **Recall** | **Precision** | **F-score** | **训练时间**     | **吞吐量**   | **配置文件**                            | **模型权重下载**                                                                                                                                                                                                |
-|---------------------|----------------|---------------|------------|------------|---------------|-------------|--------------|-----------|-------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| DBNet               | D910x1-MS2.0-G | MobileNetV3   | ImageNet       | 76.26%     | 78.22%        | 77.28%      | 10 s/epoch   | 100 img/s      | [yaml](db_mobilenetv3_icdar15.yaml) | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_mobilenetv3-62c44539.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_mobilenetv3-62c44539-f14c6a13.mindir) |
-| DBNet               | D910x8-MS2.3-G | MobileNetV3   | ImageNet       | 76.22%     | 77.98%        | 77.09%      | 1.1 s/epoch  | 960 img/s      | [yaml](db_mobilenetv3_icdar15_8p.yaml) | Coming soon                                                                                                                                                                                             |
-| DBNet               | D910x1-MS2.0-G | ResNet-18     | ImageNet       | 80.12%     | 83.41%        | 81.73%      | 9.3 s/epoch  | 108 img/s      | [yaml](db_r18_icdar15.yaml)         | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet18-0c0c4cfa.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet18-0c0c4cfa-cf46eb8b.mindir)       |
-| DBNet               | D910x1-MS2.0-G | ResNet-50     | ImageNet       | 83.53%     | 86.62%        | 85.05%      | 13.3 s/epoch | 75.2 img/s       | [yaml](db_r50_icdar15.yaml)         | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet50-c3a4aa24.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet50-c3a4aa24-fbf95c82.mindir)       |
-| DBNet               | D910x8-MS2.2-G | ResNet-50     | ImageNet       | 82.62%     | 88.54%        | 85.48%      | 2.3 s/epoch  | 435 img/s  | [yaml](db_r50_icdar15_8p.yaml)      | Coming soon                                                                                                                                                                                                     |
-|                     |                |               |            |            |               |             |              |           |                                     |                                                                                                                                                                                                           |
-| DBNet++             | D910x1-MS2.0-G | ResNet-50     | SynthText  | 85.70%     | 87.81%        | 86.74%      | 17.7 s/epoch | 56 img/s  | [yaml](db++_r50_icdar15.yaml)       | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnetpp_resnet50-068166c2.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnetpp_resnet50-068166c2-9934aff0.mindir)   |
-| DBNet++             | D910x1-MS2.2-G | ResNet-50     | SynthText  | 86.81%     | 86.85%        | 86.86%      | 12.7 s/epoch | 78.2 img/s  | [yaml](db++_r50_icdar15_910.yaml)       | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnetpp_resnet50_910-35dc71f2.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnetpp_resnet50_910-35dc71f2-e61a9c37.mindir)   |
+| **模型**              | **环境配置**        | **骨干网络**      | **预训练数据集** | **Recall** | **Precision** | **F-score** | **训练时间**     | **吞吐量**    | **配置文件**                               | **模型权重下载**                                                                                                                                                                                                      |
+|---------------------|-----------------|---------------|------------|------------|---------------|-------------|--------------|------------|----------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| DBNet               | D910x1-MS2.0-G  | MobileNetV3   | ImageNet       | 76.26%     | 78.22%        | 77.28%      | 10 s/epoch   | 100 img/s  | [yaml](db_mobilenetv3_icdar15.yaml)    | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_mobilenetv3-62c44539.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_mobilenetv3-62c44539-f14c6a13.mindir)       |
+| DBNet               | D910x8-MS2.3-G  | MobileNetV3   | ImageNet       | 76.22%     | 77.98%        | 77.09%      | 1.1 s/epoch  | 960 img/s  | [yaml](db_mobilenetv3_icdar15_8p.yaml) | Coming soon                                                                                                                                                                                                     |
+| DBNet               | D910x1-MS2.0-G  | ResNet-18     | ImageNet       | 80.12%     | 83.41%        | 81.73%      | 9.3 s/epoch  | 108 img/s  | [yaml](db_r18_icdar15.yaml)            | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet18-0c0c4cfa.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet18-0c0c4cfa-cf46eb8b.mindir)             |
+| DBNet               | D910x1-MS2.0-G  | ResNet-50     | ImageNet       | 83.53%     | 86.62%        | 85.05%      | 13.3 s/epoch | 75.2 img/s | [yaml](db_r50_icdar15.yaml)            | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet50-c3a4aa24.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet50-c3a4aa24-fbf95c82.mindir)             |
+| DBNet               | D910x8-MS2.2-G  | ResNet-50     | ImageNet       | 82.62%     | 88.54%        | 85.48%      | 2.3 s/epoch  | 435 img/s  | [yaml](db_r50_icdar15_8p.yaml)         | Coming soon                                                                                                                                                                                                     |
+|                     |                 |               |            |            |               |             |              |            |                                        |                                                                                                                                                                                                                 |
+| DBNet++             | D910x1-MS2.0-G  | ResNet-50     | SynthText  | 85.70%     | 87.81%        | 86.74%      | 17.7 s/epoch | 56 img/s   | [yaml](db++_r50_icdar15.yaml)          | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnetpp_resnet50-068166c2.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnetpp_resnet50-068166c2-9934aff0.mindir)         |
+| DBNet++             | D910x8-MS2.2-G  | ResNet-50     | SynthText  | 85.41%     | 89.55%        | 87.43%      | 1.78 s/epoch | 432 img/s  | [yaml](db++_r50_icdar15_8p.yaml)       | Coming soon                                                                                                                                                                                                     |
+| DBNet++             | D910*x1-MS2.2-G | ResNet-50     | SynthText  | 86.81%     | 86.85%        | 86.86%      | 12.7 s/epoch | 78.2 img/s | [yaml](db++_r50_icdar15_910.yaml)      | [ckpt](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnetpp_resnet50_910-35dc71f2.ckpt) \| [mindir](https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnetpp_resnet50_910-35dc71f2-e61a9c37.mindir) |
 </div>
 
 > 链接中模型DBNet的MindIR导出时的输入Shape为`(1,3,736,1280)`，模型DBNet++的MindIR导出时的输入Shape为`(1,3,1152,2048)`。

diff --git a/configs/det/dbnet/db++_r50_icdar15_8p.yaml b/configs/det/dbnet/db++_r50_icdar15_8p.yaml
@@ -0,0 +1,159 @@
+system:
+  mode: 0 # 0 for graph mode, 1 for pynative mode in MindSpore
+  distribute: True
+  amp_level: 'O0'
+  seed: 42
+  log_interval: 10
+  val_while_train: True
+  val_start_epoch: 600
+  drop_overflow_update: False
+
+model:
+  type: det
+  transform: null
+  backbone:
+    name: det_resnet50
+    pretrained: False
+  neck:
+    name: DBFPN
+    out_channels: 256
+    bias: False
+    use_asf: True             # Adaptive Scale Fusion
+    channel_attention: True   # Use channel attention in ASF
+  head:
+    name: DBHead
+    k: 50
+    bias: False
+    adaptive: True
+  pretrained: https://download.mindspore.cn/toolkits/mindocr/dbnet/dbnet_resnet50_synthtext-40655acb.ckpt
+
+postprocess:
+  name: DBPostprocess
+  box_type: quad   # whether to output a polygon or a box
+  binary_thresh: 0.3      # binarization threshold
+  box_thresh: 0.7         # box score threshold
+  max_candidates: 1000
+  expand_ratio: 1.5       # coefficient for expanding predictions
+
+metric:
+  name: DetMetric
+  main_indicator: f-score
+
+loss:
+  name: DBLoss
+  eps: 1.0e-6
+  l1_scale: 10
+  bce_scale: 5
+  bce_replace: bceloss
+
+scheduler:
+  scheduler: polynomial_decay
+  lr: 0.007
+  num_epochs: 1200
+  decay_rate: 0.9
+  warmup_epochs: 3
+
+optimizer:
+  opt: momentum
+  filter_bias_and_bn: false
+  momentum: 0.9
+  weight_decay: 1.0e-4
+
+# only used for mixed precision training
+loss_scaler:
+  type: dynamic
+  loss_scale: 512
+  scale_factor: 2
+  scale_window: 1000
+
+train:
+  ema: True
+  ckpt_save_dir: './tmp_det'
+  dataset_sink_mode: True
+  dataset:
+    type: DetDataset
+    dataset_root: /data/ocr_datasets
+    data_dir: ic15/det/train/ch4_training_images
+    label_file: ic15/det/train/det_gt.txt
+    sample_ratio: 1.0
+    transform_pipeline:
+      - DecodeImage:
+          img_mode: RGB
+          to_float32: False
+      - DetLabelEncode:
+      - RandomColorAdjust:
+          brightness: 0.1255  # 32.0 / 255
+          saturation: 0.5
+      - RandomHorizontalFlip:
+          p: 0.5
+      - RandomRotate:
+          degrees: [ -10, 10 ]
+          expand_canvas: False
+          p: 1.0
+      - RandomScale:
+          scale_range: [ 0.5, 3.0 ]
+          p: 1.0
+      - RandomCropWithBBox:
+          max_tries: 10
+          min_crop_ratio: 0.1
+          crop_size: [ 640, 640 ]
+          p: 1.0
+      - ValidatePolygons:
+      - ShrinkBinaryMap:
+          min_text_size: 8
+          shrink_ratio: 0.4
+      - BorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - NormalizeImage:
+          bgr_to_rgb: False
+          is_hwc: True
+          mean: imagenet
+          std: imagenet
+      - ToCHWImage:
+    #  the order of the dataloader list, matching the network input and the input labels for the loss function, and optional data for debug/visualize
+    output_columns: [ 'image', 'binary_map', 'mask', 'thresh_map', 'thresh_mask' ] #'img_path']
+    net_input_column_index: [ 0 ]       # input indices for network forward func in output_columns
+    label_column_index: [ 1, 2, 3, 4 ]  # input indices marked as label
+
+  loader:
+    shuffle: True
+    batch_size: 32
+    drop_remainder: True
+    num_workers: 8
+
+eval:
+  ckpt_load_path: tmp_det/best.ckpt
+  dataset_sink_mode: False
+  dataset:
+    type: DetDataset
+    dataset_root: /data/ocr_datasets
+    data_dir: ic15/det/test/ch4_test_images
+    label_file: ic15/det/test/det_gt.txt
+    sample_ratio: 1.0
+    transform_pipeline:
+      - DecodeImage:
+          img_mode: RGB
+          to_float32: False
+      - DetLabelEncode:
+      - DetResize:
+          target_size: [ 1152, 2048 ]
+          keep_ratio: True
+          padding: True
+      - NormalizeImage:
+          bgr_to_rgb: False
+          is_hwc: True
+          mean: imagenet
+          std: imagenet
+      - ToCHWImage:
+    #  the order of the dataloader list, matching the network input and the labels for evaluation
+    output_columns: [ 'image', 'polys', 'ignore_tags', 'shape_list']
+    net_input_column_index: [ 0 ] # input indices for network forward func in output_columns
+    label_column_index: [ 1, 2 ]  # input indices marked as label
+
+  loader:
+    shuffle: False
+    batch_size: 1 # TODO: due to dynamic shape of polygons (num of boxes varies), BS has to be 1
+    drop_remainder: False
+    num_workers: 2