Visualizing-CNNs-for-monocular-depth-estimation

Visualizing-CNNs-for-monocular-depth-estimation copied to clipboard

choosing densenet as Depth net (N), got keys error after loading pretrain model :

Traceback (most recent call last): File "/content/drive/MyDrive/Visualizing-CNNs-for-monocular-depth-estimation/test.py", line 133, in main() File "/content/drive/MyDrive/Visualizing-CNNs-for-monocular-depth-estimation/test.py", line 68, in main model.load_state_dict(torch.load(depth_densenet)) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1483, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for DataParallel: Missing key(s) in state_dict: "module.E.features.denseblock1.denselayer1.norm1.weight", "module.E.features.denseblock1.denselayer1.norm1.bias", "module.E.features.denseblock1.denselayer1.norm1.running_mean", "module.E.features.denseblock1.denselayer1.norm1.running_var", "module.E.features.denseblock1.denselayer1.conv1.weight", "module.E.features.denseblock1.denselayer1.norm2.weight", "module.E.features.denseblock1.denselayer1.norm2.bias", "module.E.features.denseblock1.denselayer1.norm2.running_mean", "module.E.features.denseblock1.denselayer1.norm2.running_var", "module.E.features.denseblock1.denselayer1.conv2.weight", "module.E.features.denseblock1.denselayer2.norm1.weight", "module.E.features.denseblock1.denselayer2.norm1.bias", "module.E.features.denseblock1.denselayer2.norm1.running_mean", .....