-
大佬大佬你好，我训练了 resnet18和mobilenetv3两个模型，转成onnx后 在cpu上mobilenetv3反而慢了特别多，请问是什么原因导致的?
-
which are model can help me detect text in line level (like ctpn) instead of word level?
-
https://github.com/WenmuZhou/PytorchOCR/blob/4a4f705c663dbc60563f1921b66415a953fbe12d/torchocr/networks/backbones/RecMobileNetV3.py#L136
```
if __name__ == '__main__':
import torch
from …
-
pytorch 1.7.0 windows python3.7.5
I tried to train the ocr rec model with this code, where Nn. Ctcloss was used : https://github.com/WenmuZhou/PytorchOCR/tree/master/tools/rec_train.py
Loss went d…
-
Hi, I'm trying to train with my own dataset and im getting this error ::
ake: Entering directory '/media/HDD/pytorchOCR-master/ptocr/postprocess/dbprocess'
make: 'cppdbprocess.so' is up to date.…
-
daghe updated
3 years ago
-
Hey i am trying to use the sast_resnet50 model and it requires me to download the pretrained model from baidu cloud. But i can't download from baidu. Can u upload the model to gdrive.
-
can i config the image input size is rectangle (ex: (768, 1024) instead of square?
-
https://github.com/WenmuZhou/PytorchOCR/blob/5028c9db1f2f3efea70188d27b0adcfacb89565e/tools/rec_infer.py#L33
-
index = self.dict[text[i][j]]
KeyError: 'J'
When I run rec_train.py I get the above error