RuntimeError: mat1 and mat2 shapes cannot be multiplied (8x1568 and 3872x2)

[trluper]

torch.Size([8, 1568])
Linear(in_features=3872, out_features=2, bias=True)
Traceback (most recent call last):
File "/home/wwj/SPSN/train.py", line 427, in
main()
File "/home/wwj/SPSN/train.py", line 410, in main
train(epoch, train_loader, optimizer, model, device, scheduler)
File "/home/wwj/SPSN/train.py", line 54, in train
pred, pred_ss_label, depth_pred_ss_label, pred_rely, label_rely = model(images, depths, ss_map, depth_ss_map)
File "/home/fzh/miniconda3/envs/wPy37/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/fzh/miniconda3/envs/wPy37/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 166, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/fzh/miniconda3/envs/wPy37/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/wwj/SPSN/model.py", line 546, in forward
reliance_4 = self.guide_selector(reliance_fused_feature) # reliance_4 : (N, 2)
File "/home/fzh/miniconda3/envs/wPy37/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/wwj/SPSN/model.py", line 398, in forward
x = self.fc(x)
File "/home/fzh/miniconda3/envs/wPy37/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/fzh/miniconda3/envs/wPy37/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 103, in forward
return F.linear(input, self.weight, self.bias)
File "/home/fzh/miniconda3/envs/wPy37/lib/python3.7/site-packages/torch/nn/functional.py", line 1848, in linear
return torch._C._nn.linear(input, weight, bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (8x1568 and 3872x2)

Hi，I have encountered this problem, how can I solve it

[yuluofeiyu]

Hello, where does the nju2k dataset in val_dataset come from? Is the nju2k dataset from test_dataset the original test set?thank you