LoSealL / VideoSuperResolution

A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.
MIT License
1.61k stars 295 forks source link

使用预训练模型报错 #101

Closed gaiyangjun closed 4 years ago

gaiyangjun commented 4 years ago

使用预训练的vdsr_ep0200.pth模型,运行时报错,请问什么原因,谢谢。 size mismatch for net.0.body.0.weight: copying a param with shape torch.Size([64, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 1, 3, 3])