linyu
linyu
> I reproduce TransFG code follow the instruction with overleap on 4 Tesla GPU V-100 entirely. I just got 91.2%(Paper: 91.7%) Besides, I add AutoAug in training stage as paper...
I have not reproduce VIT on CUB using TransFG, but I think the accuracy will a bit lower than 90.8% and 91.2%
I think you can view the issue of the official DARTS version, the same question was raised. And the author of the original paper replied that DARTS' s main validation...
> Dear Tianshui, when will you release the training codes? Thanks a lot. Hi，have you downloaded the pre-trained model and sucessfully got the test error? I have some problem with...
> 我找到了解决办法，preprocess的时候，你们padding的方式是四周padding，我改成右下padding就可以了，是不是训练的时候就是右下padding呢？ 我试了改成右下padding之后，onnx_export.py中的bboxes -= np.array( [pad_param[1], pad_param[0], pad_param[1], pad_param[0]])就不需要了吧？
> If I understood the problem correctly, you would like to use CaSED to tag images, correct? If so, the quickest approach is to use the [transformers](https://huggingface.co/altndrr/cased) implementation (see also...