clean-fid

clean-fid copied to clipboard

cuda error?

1

UserWarning: A NumPy version >=1.16.5 and

lcxsnow

Resize per channel reasons

1

Thanks for sharing this great work. I'm just wondering about the reasons behind resize the image per channel and not resizing it as 3 channels array. I'm referring to this...

iroilomamnou

I was trying to load a Generator from Progan implementation in pytorch. This generator receives a tensor of size `(batch_size, Z_DIM, 1, 1)` as input, where `Z_DIM` is the latent...

EvangelosTikas

Dear all, I wonder whether this module can be applied to evaluate video quality. Thanks, Junyeong Ahn

justin4ai

device=torch.device('cpu')

1

/home/m11113013/.local/lib/python3.8/site-packages/scipy/__init__.py:138: UserWarning: A NumPy version >=1.16.5 and

lcxsnow

Images in a big numpy npy file rather than in a folder

1

Thank you for your great work!! It's really helpful. I wonder if we can calculate the fid between a numpy file (.npy) that contains an array in the shape (B,...

yuanzhi-zhu

Replaced `linalg.sqrtm` with `linalg.fractional_matrix_power` to prevent numerical errors when computing the square root of sparse matrices. The previous method was causing very large complex values, especially when dealing with sparse...

dv-fenix

General question

1

Is the teaser figure depicting problems of downsampling still the same, given the new Pytorch 2.0 update? (i.e., is this issue the same for the current implementation of PyTorch bilinear...)....

Gorluxor

Hi, this is just a fix for a minor typo in fid.py and utils.py where an argument was called `custom_image_tranform` while you expected to call it `custom_image_transform` I suppose. This...

jeremyfix

Precomputed statistics for MSCOCO

1

Would be possible to add pre-computed statistics for MSCoco dataset?

ghost