@@ -13,8 +13,8 @@ comments: true
13
13
| 模型| 配置文件| 端到端| 下载链接|
14
14
| --- | --- | --- | --- |
15
15
| PP-OCRv4| | A榜 62.77% <br > B榜 62.51%| [ Model List] ( ../../ppocr/model_list.md ) |
16
- | SVTRv2(Rec Sever)| [ configs/rec/SVTRv2/rec_svtrv2_ch .yml] ( https://github.com/PaddlePaddle/PaddleOCR/tree/main/configs/rec/SVTRv2/rec_svtrv2_ch .yml ) | A榜 68.81% (使用PP-OCRv4检测模型)| [ 训练模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_svtrv2_ch_train.tar ) / [ 推理模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_svtrv2_ch_infer.tar ) |
17
- | RepSVTR(Mobile)| [ 识别] ( https://github.com/PaddlePaddle/PaddleOCR/tree/main/configs/rec/SVTRv2/rec_repsvtr_ch .yml ) <br > [ 识别蒸馏] ( https://github.com/PaddlePaddle/PaddleOCR/tree/main/configs/rec/SVTRv2/rec_svtrv2_ch_distillation .yml ) <br > [ 检测] ( https://github.com/PaddlePaddle/PaddleOCR/tree/main/configs/det/det_repsvtr_db.yml ) | B榜 65.07%| 识别: [ 训练模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_repsvtr_ch_train.tar ) / [ 推理模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_repsvtr_ch_infer.tar ) <br > 识别蒸馏: [ 训练模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_svtrv2_distill_ch_train.tar ) / [ 推理模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_svtrv2_distill_ch_infer.tar ) <br > 检测: [ 训练模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_det_repsvtr_ch_train.tar ) / [ 推理模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_det_repsvtr_ch_infer.tar ) |
16
+ | SVTRv2(Rec Sever)| [ configs/rec/SVTRv2/ch_SVTRv2_rec .yml] ( https://github.com/PaddlePaddle/PaddleOCR/tree/main/configs/rec/SVTRv2/ch_SVTRv2_rec .yml ) | A榜 68.81% (使用PP-OCRv4检测模型)| [ 训练模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_svtrv2_ch_train.tar ) / [ 推理模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_svtrv2_ch_infer.tar ) |
17
+ | RepSVTR(Mobile)| [ 识别] ( https://github.com/PaddlePaddle/PaddleOCR/tree/main/configs/rec/SVTRv2/ch_RepSVTR_rec .yml ) <br > [ 识别蒸馏] ( https://github.com/PaddlePaddle/PaddleOCR/tree/main/configs/rec/SVTRv2/ch_SVTRv2_rec_distillation .yml ) <br > [ 检测] ( https://github.com/PaddlePaddle/PaddleOCR/tree/main/configs/det/det_repsvtr_db.yml ) | B榜 65.07%| 识别: [ 训练模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_repsvtr_ch_train.tar ) / [ 推理模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_repsvtr_ch_infer.tar ) <br > 识别蒸馏: [ 训练模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_svtrv2_distill_ch_train.tar ) / [ 推理模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_rec_svtrv2_distill_ch_infer.tar ) <br > 检测: [ 训练模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_det_repsvtr_ch_train.tar ) / [ 推理模型] ( https://paddleocr.bj.bcebos.com/openatom/openatom_det_repsvtr_ch_infer.tar ) |
18
18
19
19
🚀 快速使用:参考PP-OCR推理[ 说明文档] ( https://github.com/PaddlePaddle/PaddleOCR/blob/main/doc/doc_ch/inference_ppocr.md ) ,将检测和识别模型替换为上表中对应的RepSVTR或SVTRv2推理模型即可使用。
20
20
@@ -30,22 +30,22 @@ comments: true
30
30
31
31
``` bash linenums="1"
32
32
# 单卡训练(训练周期长,不建议)
33
- python3 tools/train.py -c configs/rec/SVTRv2/rec_repsvtr_gtc .yml
33
+ python3 tools/train.py -c configs/rec/SVTRv2/ch_RepSVTR_rec_gtc .yml
34
34
35
35
# 多卡训练,通过--gpus参数指定卡号
36
36
# Rec 学生模型
37
- python -m paddle.distributed.launch --gpus ' 0,1,2,3,4,5,6,7' tools/train.py -c configs/rec/SVTRv2/rec_repsvtr_gtc .yml
37
+ python -m paddle.distributed.launch --gpus ' 0,1,2,3,4,5,6,7' tools/train.py -c configs/rec/SVTRv2/ch_RepSVTR_rec_gtc .yml
38
38
# Rec 教师模型
39
- python -m paddle.distributed.launch --gpus ' 0,1,2,3,4,5,6,7' tools/train.py -c configs/rec/SVTRv2/rec_svtrv2_gtc .yml
39
+ python -m paddle.distributed.launch --gpus ' 0,1,2,3,4,5,6,7' tools/train.py -c configs/rec/SVTRv2/ch_SVTRv2_rec_gtc .yml
40
40
# Rec 蒸馏训练
41
- python -m paddle.distributed.launch --gpus ' 0,1,2,3,4,5,6,7' tools/train.py -c configs/rec/SVTRv2/rec_svtrv2_gtc_distill .yml
41
+ python -m paddle.distributed.launch --gpus ' 0,1,2,3,4,5,6,7' tools/train.py -c configs/rec/SVTRv2/ch_SVTRv2_rec_gtc_distill .yml
42
42
```
43
43
44
44
### 3.2 评估
45
45
46
46
``` bash linenums="1"
47
47
# 注意将pretrained_model的路径设置为本地路径。
48
- python3 -m paddle.distributed.launch --gpus ' 0' tools/eval.py -c configs/rec/SVTRv2/rec_repsvtr_gtc .yml -o Global.pretrained_model=output/rec_repsvtr_gtc /best_accuracy
48
+ python3 -m paddle.distributed.launch --gpus ' 0' tools/eval.py -c configs/rec/SVTRv2/ch_RepSVTR_rec_gtc .yml -o Global.pretrained_model=output/ch_RepSVTR_rec_gtc /best_accuracy
49
49
```
50
50
51
51
### 3.3 预测
@@ -54,7 +54,7 @@ python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/SVT
54
54
55
55
``` bash linenums="1"
56
56
# 注意将pretrained_model的路径设置为本地路径。
57
- python3 tools/infer_rec.py -c tools/eval.py -c configs/rec/SVTRv2/rec_repsvtr_gtc .yml -o Global.pretrained_model=output/rec_repsvtr_gtc /best_accuracy Global.infer_img=' ./doc/imgs_words_en/word_10.png'
57
+ python3 tools/infer_rec.py -c tools/eval.py -c configs/rec/SVTRv2/ch_RepSVTR_rec_gtc .yml -o Global.pretrained_model=output/ch_RepSVTR_rec_gtc /best_accuracy Global.infer_img=' ./doc/imgs_words_en/word_10.png'
58
58
# 预测文件夹下所有图像时,可修改infer_img为文件夹,如 Global.infer_img='./doc/imgs_words_en/'。
59
59
```
60
60
@@ -66,7 +66,7 @@ python3 tools/infer_rec.py -c tools/eval.py -c configs/rec/SVTRv2/rec_repsvtr_gt
66
66
67
67
``` bash linenums="1"
68
68
# 注意将pretrained_model的路径设置为本地路径。
69
- python3 tools/export_model.py -c configs/rec/SVTRv2/rec_repsvtr_gtc .yml -o Global.pretrained_model=output/rec_repsvtr_gtc /best_accuracy Global.save_inference_dir=./inference/rec_repsvtr_infer
69
+ python3 tools/export_model.py -c configs/rec/SVTRv2/ch_RepSVTR_rec_gtc .yml -o Global.pretrained_model=output/ch_RepSVTR_rec_gtc /best_accuracy Global.save_inference_dir=./inference/rec_repsvtr_infer
70
70
```
71
71
72
72
** 注意:** 如果您是在自己的数据集上训练的模型,并且调整了字典文件,请注意修改配置文件中的` character_dict_path ` 是否为所正确的字典文件。
0 commit comments