Closed xuanzhangyang closed 6 years ago
Hello.
You have to put additional arguments(--n_resblocks
, --n_feats
, and --res_scale
) to test that model.
Please refer to this line!
Also, I recommend you to use --chop
argument if there is any trouble with GPU memory.
Thank you.
**Additional description
This happens because PyTorch does not save model structure when we make checkpoints.
It means that pre-trained models only contain parameters, but not structures.
Therefore, we have to build the model first to load those parameters.
Default setting is EDSR_baseline_x4, which has 16 resblocks and 64 channels per layer.
If you do not specify those arguments, an error occurs because you are trying to load the parameters from the model with 32 resblocks and 256 channels per layer.
The problem has been solved.
Thank you.
I download pre-train model and test like this:
but i get an error