Open ayst123 opened 6 years ago
Please use pickle to load the parameters stored in the pkl file, following the lines 43-49 in networks.py.
import pickle
f = file('wavelet_weights_c2.pkl','rb')
dct = pickle.load(f)
f.close()
Thanks for the reply. But I am still confused. The pkl file is only for WaveletTransform? How to load parameters for the NetSR(). I am not sure what should we give for "--pretrained".
Is it possible to have the detailed instruction on how to test image using the existing parameters ? Thanks
Can I ask where is the pretrained model for srnet? It seems that pkl file is for the module, WaveletTransform, but not srnet. Thanks
I have the same question with the variable pretrained.
The pkl file can not be loaded using the method presented in the second floor.
The error is like that:
Traceback (most recent call last):
File "test_tmp.py", line 4, in
Do you know what's wrong with it?
@unlabeledData pickle.load(file, encoding='latin1')
how to load WaveletTransform's weights when upscale factor == 8? @hhb072
wavelet_weights_c2.pkl
where can i get this weights ????
@TuXiaokang Thank you, it works when I add (encoding='latin1')
Hi,
It seems the uploaded model doesn't work. is it possible to update it? Thanks!