search

zhanglonghao1992 / One-Shot_Free-View_Neural_Talking_Head_Synthesis

Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"
Other
735 stars 141 forks source link

inference error #64

Closed 307509256 closed 1 year ago

307509256 commented 1 year ago

size mismatch for first.conv.weight: copying a param with shape torch.Size([64, 3, 7, 7]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3]).

zhanglonghao1992 commented 1 year ago

@307509256 Check carefully whether the model and config file you use are aligned