Merge remote-tracking branch 'upstream/develop' into zxdev

This commit is contained in:
zhangxin 2020-06-24 19:06:18 +08:00
commit 9136cba8cb
4 changed files with 15 additions and 13 deletions

View File

@ -43,10 +43,8 @@ PaddleOCR已完成Windows和Mac系统适配运行时注意两点1、在[
其中,公开数据集都是开源的,用户可自行搜索下载,也可参考[中文数据集](./datasets.md),合成数据暂不开源,用户可使用开源合成工具自行合成,可参考的合成工具包括[text_renderer](https://github.com/Sanster/text_renderer)、[SynthText](https://github.com/ankush-me/SynthText)、[TextRecognitionDataGenerator](https://github.com/Belval/TextRecognitionDataGenerator)等。
10. **使用带TPS的识别模型预测报错**
报错信息Input(X) dims[3] and Input(Grid) dims[2] should be equal, but received X dimension[3](320) != Grid dimension[2](100)
原因TPS模块暂时无法支持变长的输入请设置 --rec_image_shape='3,32,100' --rec_char_type='en' 固定输入shape
11. **自定义字典训练的模型,识别结果出现字典里没出现的字**
预测时没有设置采用的自定义字典路径。设置方法是在预测时通过增加输入参数rec_char_dict_path来设置。

View File

@ -127,7 +127,7 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_
## 文本识别模型推理
下面将介绍超轻量中文识别模型推理和基于CTC损失的识别模型推理。**而基于Attention损失的识别模型推理还在调试中**。对于中文文本识别建议优先选择基于CTC损失的识别模型实践中也发现基于Attention损失的效果不如基于CTC损失的识别模型。
下面将介绍超轻量中文识别模型推理、基于CTC损失的识别模型推理和基于Attention损失的识别模型推理。对于中文文本识别建议优先选择基于CTC损失的识别模型实践中也发现基于Attention损失的效果不如基于CTC损失的识别模型。此外,如果训练时修改了文本的字典,请参考下面的自定义文本识别字典的推理。
### 1.超轻量中文识别模型推理

View File

@ -45,7 +45,5 @@ At present, the open source model, dataset and magnitude are as follows:
Among them, the public datasets are opensourced, users can search and download by themselves, or refer to [Chinese data set](./datasets_en.md), synthetic data is not opensourced, users can use open-source synthesis tools to synthesize data themselves. Current available synthesis tools include [text_renderer](https://github.com/Sanster/text_renderer), [SynthText](https://github.com/ankush-me/SynthText), [TextRecognitionDataGenerator](https://github.com/Belval/TextRecognitionDataGenerator), etc.
10. **Error in using the model with TPS module for prediction**
Error message: Input(X) dims[3] and Input(Grid) dims[2] should be equal, but received X dimension[3](108) != Grid dimension[2](100)
SolutionTPS does not support variable shape. Please set --rec_image_shape='3,32,100' and --rec_char_type='en'

View File

@ -59,7 +59,13 @@ def cal_det_res(exe, config, eval_info_dict):
img_list.append(data[ino][0])
ratio_list.append(data[ino][1])
img_name_list.append(data[ino][2])
try:
img_list = np.concatenate(img_list, axis=0)
except:
err = "concatenate error usually caused by different input image shapes in evaluation or testing.\n \
Please set \"test_batch_size_per_card\" in main yml as 1\n \
or add \"test_image_shape: [h, w]\" in reader yml for EvalReader."
raise Exception(err)
outs = exe.run(eval_info_dict['program'], \
feed={'image': img_list}, \
fetch_list=eval_info_dict['fetch_varname_list'])