Tabsun

This function is loading data structures(image, text...) on CPU memory into torch tensor variable on GPU, I think.

这个alphabet需要自己整理，可以直接把train lmdb里当文字集合成set就行了

@GitHubGS When t[i] == 0, self.alphabet[0-1] is the last one in alphabet. It means a separator between characters. Actually the added '-' only make sense in decode() and it wont...

I also got different outputs under py2 and py3. Finally I figure out the difference is caused by the following lines: https://github.com/lukemelas/EfficientNet-PyTorch/blob/7e8b0d312162f335785fb5dcfa1df29a75a1783a/efficientnet_pytorch/utils.py#L189 https://github.com/lukemelas/EfficientNet-PyTorch/blob/7e8b0d312162f335785fb5dcfa1df29a75a1783a/efficientnet_pytorch/utils.py#L190 and https://github.com/lukemelas/EfficientNet-PyTorch/blob/7e8b0d312162f335785fb5dcfa1df29a75a1783a/efficientnet_pytorch/utils.py#L240 The division operation give different...

> @abhigoku10 I have deleted DCNv2 from my repo. Check again this link https://github.com/CharlesShang/DCNv2 readme. it now has a line that says run python testcpu.py to check if it runs...

npy files are the pretrained model which is taken as start model in training. You can get the *.npy files by models/numpy/download.sh.

Really expect for some suggestions :D

any update on this question?

> I'm not one of the authors but I assume that they took the PCA of a bunch of images and then took the vector of the first component (`pca.components_[0]`)....

@blackarrow3542 Have you solved the problem? I encountered the same error, and it seems I need to calibrate the graph but I have no idea how to make it. Any...