UNet3DConditionModel: size mismatch for conv_in.weight: copying a param with shape torch.Size([320, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 9, 3, 3]).

alibaba-yuanjing-aigclab / ViViD

ViViD: Video Virtual Try-on using Diffusion Models

Apache License 2.0

368 stars 23 forks source link

UNet3DConditionModel: size mismatch for conv_in.weight: copying a param with shape torch.Size([320, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 9, 3, 3]). #6

Open agsoft-lee opened 3 weeks ago

agsoft-lee commented 3 weeks ago

UNet3DConditionModel: size mismatch for conv_in.weight: copying a param with shape torch.Size([320, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 9, 3, 3]).