CFCNet
CFCNet copied to clipboard

choyingw

→

Metadata

NeurIPS 2019: Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion

Reame
Issues

Results 1 CFCNet issues

Sort by recently updated

Pretained NYU error

I downloaded the pretrained nyu weights (500.pth), and edited line 138 of base_model.py to state_dict = torch.load('.../500.pth', map_location=str(self.device)) When I run python evaluate.py --name nyu --checkpoints_dir ... --train_path ~/nyudepthv2/nyudepthv2/val/ --test_path...

haozhen315