chinmay1148
commented
2 years ago this issue is resolved. Caused due to commenting out the transforms function in dataset/scannet.py
Closed chinmay1148 closed 2 years ago
chinmay1148
commented
2 years ago this issue is resolved. Caused due to commenting out the transforms function in dataset/scannet.py
Traceback (most recent call last): File "main.py", line 310, in
train()
File "main.py", line 214, in train
loss, scalar_outputs = train_sample(sample) ### Training is done here
File "main.py", line 290, in train_sample
outputs, loss_dict = model(sample)
File "/usr/local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, kwargs)
File "/usr/local/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 166, in forward
return self.module(*inputs[0], *kwargs[0])
File "/usr/local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(input, kwargs)
File "/gpfs-volume/NeuralRecon-rgbd/models/neuralrecon.py", line 119, in forward
outputs, loss_dict = self.neucon_net(features, inputs, outputs)
File "/usr/local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/gpfs-volume/NeuralRecon-rgbd/models/neucon_network.py", line 130, in forward
volume, count = back_project(up_coords, inputs['vol_origin_partial'], self.cfg.VOXEL_SIZE, feats,
KeyError: 'vol_origin_partial'
The key 'vol_origin_partial' is not present in generate_gt.py while generating the fragment.pkl file. This information is needed in back_proj function.