search

JingZhang617 / UCNet

UC-Net: Uncertainty Inspired RGB-D Saliency Detectionvia Conditional Variational Autoencoders, CVPR2020
178 stars 25 forks source link

loading tested model error----tensor size mismatch #4

Open huanglf714 opened 4 years ago

huanglf714 commented 4 years ago

i download the model_100_gen.pth and load it in the test.py when i run the test.py,the error is : size mismatch for sal_encoder.conv_depth1.conv.weight: copying a param with shape torch.Size([3, 9, 3, 3]) from checkpoint, the shape in current model is torch.Size([3, 14, 3, 3]).

nnizhang commented 4 years ago

I got the same error when loading the model_100_gen.pth. error details: size mismatch for sal_encoder.conv_depth1.conv.weight: copying a param with shape torch.Size([3, 9, 3, 3]) from checkpoint, the shape in current model is torch.Size([3, 14, 3, 3]).

JingZhang617 commented 4 years ago

Hi, I have updated the test.py file and can you please download the new test file and try again?

Cheers, Jing

On Thu, 9 Jul 2020 at 11:41, nnizhang notifications@github.com wrote:

I got the same error when loading the model_100_gen.pth. error details: size mismatch for sal_encoder.conv_depth1.conv.weight: copying a param with shape torch.Size([3, 9, 3, 3]) from checkpoint, the shape in current model is torch.Size([3, 14, 3, 3]).

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/JingZhang617/UCNet/issues/4#issuecomment-655845328, or unsubscribe https://github.com/notifications/unsubscribe-auth/AE6B4F2RVEGYDUNE53CGUUDR2UN23ANCNFSM4OKBMMFQ .

-- Jing Zhang Ph.D. Student College of Engineering and Computer Science, Australian National University. Email: zjnwpu@gmail.com