-
问题描述：使用models\PaddleCV\ocr_recognition训练attention模型（crnn_ctc模型使用正常），并在infer.py中重新保存为固化模型，使用paddle predictor预测报错，错误信息为：
File "D:\pythonAPI\Python37\call_paddle_OCR.py", line 108, in test_image
…
-
Hi jaybdub,
If I got a tensor which has x.shape = [1,1024,22], and I want to permute the dims with x = x.permute(2,0,1) but it went wrong(AssertionError).What should I do to get the same result and…
-
我在windows上部署的，所以没有用darknet，直接选择了opencv的dnn模块。
其他部分都很正常，ocr部分，crnn在GPU下只用了不到0.5秒。
但是opecv的dnn模块做yolo检测，用了两秒半，我想是没有使用GPU。
但我在网上搜索了很久也没有弄懂要怎么才能让opencv的dnn支持CUDA。
希望能指导一下，非常感谢。
-
my memory is 8 GB (DDR4 2400MHz),however it's still not enough.how can i deal with this problem?
```
C:\Users\jack\Desktop>python lal.python
2020-05-22 21:32:45.116443: W tensorflow/stream_executo…
-
https://zhuanlan.zhihu.com/p/43534801
-
- I'm trying out OCR projects using CRNN models. This error occurred when the program is executed to model.fit. I tried to use several methods to solve the problem, but nothing seemed to work.
I am …
-
错误：`PaddleCheckError: out of memory at [/paddle/paddle/fluid/platform/device_context.cc:219]`
- 版本、环境信息：
1）PaddlePaddle版本：1.6 release版
2）GPU：P4、CUDA10和CUDNN7.6
4）系统环境：centos7,Python版本:…
-
Traceback (most recent call last):
File "crnn_main_v2.py", line 183, in
main(crnn, train_loader, val_loader, criterion, optimizer)
File "crnn_main_v2.py", line 115, in main
train(crnn…
-
请教：通用中文OCR与轻量级的区别在哪？
-
感谢大佬分享，太强了
请问现在提供的中文模型只有inference.md中的两种吗？