BugsMaker

training error in stage 1

29

File "Moore-AnimateAnyone/src/models/mutual_self_attention.py", line 180, in hacked_basic_transformer_inner_forward norm_hidden_states[_uc_mask], IndexError: The shape of the mask [2] at index 0 does not match the shape of the indexed tensor [3, 9216, 320] at...

请问stage1和stage2分别使用了哪些数据集？

有办法降低一下显存占用吗

7

V100 32G能不能训起来？

Can mmhuman3d support densepose?

Total trainable params 0 ValueError: optimizer got an empty parameter list

hack_poseguider

1

in hack_poseguider line 40: self.scale = nn.Parameter(torch.ones(1) * 2) in poseguider line 48: self.scale = nn.Parameter(torch.ones(1)) Could you please explain the difference?

AnimateAnyone用10个tiktok style videos做test，请问这10个videos在哪里下载？

1

AnimateAnyone用10个tiktok style videos做test，请问这10个videos在哪里下载？

Some top layer parames of reference_unet don't need grad, what is the reason?

1

# Some top layer parames of reference_unet don't need grad for name, param in reference_unet.named_parameters(): if "up_blocks.3" in name: param.requires_grad_(False) else: param.requires_grad_(True)

How can I get "More TikTok-Style Training Data" please?

1

How can I get "More TikTok-Style Training Data" please?