PaddleOCR
PaddleOCR copied to clipboard
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and de...
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - docker镜像:pipeline_serving_demo registry.baidubce.com/paddlepaddle/serving:0.9.0-cuda11.2-cudnn8-runtime config.yml配置文件内容: ``` # 批量查询Serving的数量, 默认1。batch_size>1要设置auto_batching_timeout,否则不足batch_size时会阻塞 batch_size: 16 # 批量查询超时,与batch_size配合使用 auto_batching_timeout: 2000 ``` 使用Serving/examples/Pipeline/PaddleOCR/ocr/benchmark.sh脚本进行测试
增值税发票结构化识别是什么思路呢?
ser 训练报错
'remote_prefetch', False, 'padding_idx', padding_idx) ValueError: (InvalidArgument) Variable value (input) of OP(fluid.layers.embedding) expected >= 0 and < 1024, but got -50. Please check input value. [Hint: Expected ids[i] >= 0, but...
使用官方表格结构预测模型识别表格,对比中文表格和英文表格,发现中文表格的结构识别效果比较差。 请问,如果想要提升中文表格结构识别能力,是否要再根据中文表格进行训练。 谢谢!
自己找了30w张,全域的样本图片(既包含生僻字也有普通字),感觉提升效果很一般。 生僻字的识别没有明显的提升,特殊字体略有提升,但是对于普通字体识别率有所下降。 有没有针对的优化建议呢,谢谢
psdz@gpu-2080:~/lcl/PaddleOCR$ python3 tools/train.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrain Traceback (most recent call last): File "/home/psdz/lcl/PaddleOCR/tools/train.py", line 27, in import paddle ModuleNotFoundError: No module named 'paddle' (paddle_lcl) psdz@gpu-2080:~/lcl/PaddleOCR$ pip install paddle Looking...
I trained the Paddle detection model with my own custom data, and it get the best accuracy and latest model. when i tried to export it and convert it to...
Croatian language characters [croatian_dict.txt](https://github.com/PaddlePaddle/PaddleOCR/files/8684263/croatian_dict.txt) Characters used in Croatian language; skipped "double character letters" like "dž", "lj", "nj". [Wikipedia](https://en.wikipedia.org/wiki/Gaj%27s_Latin_alphabet)
The problem doesn't exist when I run paddleocr alone, but if I load the torch model, the problem occurs. ``` Traceback (most recent call last): File "/home/xingyum/anaconda3/envs/vis/lib/python3.10/runpy.py", line 196, in...
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment:无 - 版本号/Version:Paddle:无 PaddleOCR: 问题相关组件/Related components:无 - 运行指令/Command Code:无 - 完整报错/Complete Error Message:无 问下你们的svtr在那个阶段?  backbone是mobilenetv1enhance, 而svtr代码也在backbone下,却没用到