Open nathantew14 opened 3 years ago
You can download resnet101-5d3b4d8f.pth at 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth'. When you test on the pretrained models named IOG_PASCAL_SBD.pth,you need to change the ‘pretrain_dict = torch.load(os.path.join(save_dir, 'models', modelName + '_epoch-' + str(resume_epoch - 1) + '.pth'))’ to ‘pretrain_dict = torch.load( '/path/to/IOG_PASCAL_SBD.pth')’ in test.py. If you want to finetune on the pretrained models named IOG_PASCAL_SBD.pth,you need to modify the lines 63-70 in train.py.
In
train.py
, the code attempts to load a pretrained model by callingNetwork()
. The default path to the pretrained model in the code inmypath.py
is'/path/to/models/resnet101-5d3b4d8f.pth'
, but no such file is found. I assumed the user had to insert the actual path manually, so I tried to do so with both pretrained models provided in thereadme.md
file, namelyIOG_PASCAL.pth
andIOG_PASCAL_SBD.pth
, but both returned error:KeyError: 'conv1.weight'
Are those the right pretrained models to use? If not, what are? Thanks.
P.S. Looking forward to the demo code, any ETA?