Inference not working for dimension unmatched

[KurokyLee]

Traceback (most recent call last):
File "inference_gcfsr_blind.py", line 69, in
main()
File "inference_gcfsr_blind.py", line 66, in main
generate(args, img, model, device, imgname)
File "inference_gcfsr_blind.py", line 19, in generate
output, _ = g_ema(img)
File "/data/lichengyu/miniconda3/envs/gcfsr/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/data/lichengyu/projects/GCFSR-main/basicsr/archs/gcfsr_arch.py", line 1133, in forward
out = conv2(out, latent[:, i], noise=noise2, scale1=scales1[j], scale2=scales2[j], shift=shifts[j])
File "/data/lichengyu/miniconda3/envs/gcfsr/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/data/lichengyu/projects/GCFSR-main/basicsr/archs/gcfsr_arch.py", line 741, in forward
out = out * scale1.view(-1, out.size(1), 1, 1) + shift * scale2.view(-1, out.size(1), 1, 1)
RuntimeError: The size of tensor a (14) must match the size of tensor b (15) at non-singleton dimension 2