Closed ldkong1205 closed 1 year ago
Hi, Thank you for your interest. I'm sorry for this confusion. Is your code up-to-date? If so, please use the weights in models/diffnet_640x192 instead.
Hi, Thank you for your interest. I'm sorry for this confusion. Is your code up-to-date? If so, please use the weights in models/diffnet_640x192 instead.
Hi @brandleyzhou, thank you for your reply! Yes, I am using the latest code and I have tried the checkpoints in models/diffnet_640x192
, too, but the problem still exists. Could you please have a look? Thanks!
From my side, the encoder_dict
and decoder_dict
are loading the exact same number of keys, which should all belong to the encoder.
ncoder_dict = torch.load(encoder_path) if torch.cuda.is_available() else torch.load(encoder_path,map_location = 'cpu')
decoder_dict = torch.load(decoder_path) if torch.cuda.is_available() else torch.load(encoder_path,map_location = 'cpu')
Then I found that this line has a typo: the decoder_dict
should load from decoder_path
instead of encoder_path
. I think you might want to modify this.
Yes, you are right. if you use cuda/gpu to test, the code is ok. but in the other case, the decoder would be loaded wrong weights. Thanks for pointing it out.
Yes, you are right. if you use cuda/gpu to test, the code is ok. but in the other case, the decoder would be loaded wrong weights. Thanks for pointing it out.
Right. Thanks!
Hi @brandleyzhou, thank you for your great work!
I met the following problem when testing your pretrained models:
The pretrained weights are downloaded from this repository page. Specifically, I was testing two pretrained models:
Could you please have a look at this and upload the complete models? Thanks in advance!