updata train_test doc for tta

open-mmlab · Feb 16, 2023 · f021ca2 · f021ca2
1 parent 1ad8567
commit f021ca2
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 7 deletions.
diff --git a/configs/textrecog/crnn/README.md b/configs/textrecog/crnn/README.md
@@ -33,11 +33,11 @@ Image-based sequence recognition has been a long-standing research topic in comp
 
 ## Results and models
 
-|                        methods                         |        | Regular Text |           |     |           | Irregular Text |        |                                        download                                         |
-| :----------------------------------------------------: | :----: | :----------: | :-------: | :-: | :-------: | :------------: | :----: | :-------------------------------------------------------------------------------------: |
-|                        methods                         | IIIT5K |     SVT      | IC13-1015 |     | IC15-2077 |      SVTP      |  CT80  |                                                                                         |
-| [CRNN](/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py) | 0.8053 |    0.7991    |  0.8739   |     |  0.5571   |     0.6093     | 0.5694 | [model](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/crnn_mini-vgg_5e_mj_20220826_224120-8afbedbb.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/20220826_224120.log) |
-|                       CRNN-TTA)                        | 0.8013 |    0.7975    |  0.8631   |     |  0.5763   |     0.6093     | 0.5764 | [model](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/crnn_mini-vgg_5e_mj_20220826_224120-8afbedbb.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/20220826_224120.log) |
+|                          methods                           |        | Regular Text |           |     |           | Irregular Text |        |                                      download                                       |
+| :--------------------------------------------------------: | :----: | :----------: | :-------: | :-: | :-------: | :------------: | :----: | :---------------------------------------------------------------------------------: |
+|                          methods                           | IIIT5K |     SVT      | IC13-1015 |     | IC15-2077 |      SVTP      |  CT80  |                                                                                     |
+|   [CRNN](/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py)   | 0.8053 |    0.7991    |  0.8739   |     |  0.5571   |     0.6093     | 0.5694 | [model](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/crnn_mini-vgg_5e_mj_20220826_224120-8afbedbb.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/20220826_224120.log) |
+| [CRNN-TTA](/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py) | 0.8013 |    0.7975    |  0.8631   |     |  0.5763   |     0.6093     | 0.5764 | [model](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/crnn_mini-vgg_5e_mj_20220826_224120-8afbedbb.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/20220826_224120.log) |
 
 ## Citation
 

diff --git a/docs/en/user_guides/train_test.md b/docs/en/user_guides/train_test.md
@@ -36,6 +36,7 @@ The following table lists all the arguments supported by `train.py`. Args withou
 | --cfg-options   | str  | Override some settings in the configs. [Example](<>)                        |
 | --launcher      | str  | Option for launcher，\['none', 'pytorch', 'slurm', 'mpi'\].                 |
 | --local_rank    | int  | Rank of local machine，used for distributed training，defaults to 0。       |
+| --tta           | bool | Whether to use test time augmentation.                                      |
 
 ### Test
 
@@ -308,3 +309,15 @@ The visualization-related parameters in `tools/test.py` are described as follows
 | --show      | bool  | Whether to show the visualization results.    |
 | --show-dir  | str   | Path to save the visualization results.       |
 | --wait-time | float | Interval of visualization (s), defaults to 2. |
+
+### Test Time Augmentation
+
+Test time augmentation (TTA) is a technique that is used to improve the performance of a model by performing data augmentation on the input image at test time. It is a simple yet effective method to improve the performance of a model. In MMOCR, we support TTA in the following ways:
+
+```{note}
+TTA is only supported for text recognition models.
+```
+
+```bash
+python tools/test.py configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py checkpoints/crnn_mini-vgg_5e_mj.pth --tta
+```
diff --git a/docs/zh_cn/user_guides/train_test.md b/docs/zh_cn/user_guides/train_test.md
@@ -66,6 +66,7 @@ CUDA_VISIBLE_DEVICES=0 python tools/test.py configs/textdet/dbnet/dbnet_resnet50
 | --cfg-options | str   | 用于覆写配置文件中的指定参数。[示例](#添加示例)                |
 | --launcher    | str   | 启动器选项，可选项目为 \['none', 'pytorch', 'slurm', 'mpi'\]。 |
 | --local_rank  | int   | 本地机器编号，用于多机多卡分布式训练，默认为 0。               |
+| --tta         | bool  | 是否使用测试时数据增强                                         |
 
 ## 多卡机器训练及测试
 
@@ -308,3 +309,16 @@ python tools/test.py configs/textdet/dbnet/dbnet_r50dcnv2_fpnc_1200e_icdar2015.p
 | --show      | bool  | 是否绘制可视化结果。             |
 | --show-dir  | str   | 可视化图片存储路径。             |
 | --wait-time | float | 可视化间隔时间（秒），默认为 2。 |
+
+### 测试时数据增强
+
+测试时增强，指的是在推理（预测）阶段，将原始图片进行水平翻转、垂直翻转、对角线翻转、旋转角度等数据增强操作，得到多张图，分别进行推理，再对多个结果进行综合分析，得到最终输出结果。
+为此，MMOCR 提供了一键式测试时数据增强，仅需在测试时添加 `--tta` 参数即可。
+
+```{note}
+TTA 仅支持文本识别模型。
+```
+
+```bash
+python tools/test.py configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py checkpoints/crnn_mini-vgg_5e_mj.pth --tta
+```
diff --git a/tools/test.py b/tools/test.py
@@ -109,8 +109,6 @@ def main():
     if args.show or args.show_dir:
         cfg = trigger_visualization_hook(cfg, args)
 
-    cfg.load_from = args.checkpoint
-
     if args.tta:
         cfg.test_dataloader.dataset.pipeline = cfg.tta_pipeline
         cfg.tta_model.module = cfg.model