ivonatau

Results 6 comments of ivonatau

pre-trained models sharing on other cloud storage?

I cannot extract the OneDrive tar. It seems the package is corrupted

size mismatch for encoder.weight: copying a param with shape torch.Size([5450, 300]) from checkpoint, the shape in current model is torch.Size([279, 300]).

Got the same issue. The problem was wrong encoder model path in `cfg/{}.attn2.yml`file.

ValueError: some of the strides of a given numpy array are negative.

I had the same error and and was able to fix it by copying the numpy array (the indices are thus turned positive) : ``` packed_desc = nn.utils.rnn.pack_padded_sequence( desc[sorted_indices.copy(), ...].transpose(0,...

Support for StyleGAN2-ADA

OK, I actually made it work by using the original stylegan2-ada repo with the following modfied `blend_models.py` script added to the main directory: ``` import tensorflow as tf import sys,...

Please Answer . Nothing works.

@Fizmath I am sorry for the issues, this repository comes from an old project that was more experimental than production-ready code. Moreover, many of the libraries that the app depended...

The training loss

What batch size are you using?