rasd3 / 3d-dual-fusion Goto Github PK

Hello, what should I do when I encounter these problems

File "./tools/train.py", line 201, in
main()
File "./tools/train.py", line 170, in main
merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch
File "/home/wht/wht/3D-Dual-Fusion-master/VoxelRCNN/tools/train_utils/train_utils.py", line 118, in train_model
dataloader_iter=dataloader_iter
File "/home/wht/wht/3D-Dual-Fusion-master/VoxelRCNN/tools/train_utils/train_utils.py", line 25, in train_one_epoch
batch = next(dataloader_iter)
File "/home/wht/anaconda3/envs/EPNet/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/home/wht/anaconda3/envs/EPNet/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
return self._process_data(data)
File "/home/wht/anaconda3/envs/EPNet/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
data.reraise()
File "/home/wht/anaconda3/envs/EPNet/lib/python3.7/site-packages/torch/_utils.py", line 425, in reraise
raise self.exc_type(msg)
UnboundLocalError: Caught UnboundLocalError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/wht/anaconda3/envs/EPNet/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/home/wht/anaconda3/envs/EPNet/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/wht/anaconda3/envs/EPNet/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/wht/wht/3D-Dual-Fusion-master/VoxelRCNN/pcdet/datasets/kitti/kitti_dataset.py", line 435, in getitem
data_dict = self.prepare_data(data_dict=input_dict)
File "/home/wht/wht/3D-Dual-Fusion-master/VoxelRCNN/pcdet/datasets/dataset.py", line 133, in prepare_data
'gt_boxes_mask': gt_boxes_mask
File "/home/wht/wht/3D-Dual-Fusion-master/VoxelRCNN/pcdet/datasets/augmentor/data_augmentor.py", line 243, in forward
data_dict = cur_augmentor(data_dict=data_dict)
File "/home/wht/wht/3D-Dual-Fusion-master/VoxelRCNN/pcdet/datasets/augmentor/database_sampler.py", line 403, in call
mv_height = mv_height[valid_mask]
UnboundLocalError: local variable 'mv_height' referenced before assignment

How does the AGFN work in Transfusion，in the code，I just see the transformer to fuse point to image，rather than the gated fusion mechanism

Hi, this a very excellent project. I would like to quickly implement your project, could you please provide me with a complete runtime environment, e.g. upload your environment on DockerHub or provide a detailed tutorial on how to install it. I would appreciate it if you could provide it!

Thank you very much for your assistance! I am currently replicating your project, but I encountered an issue when trying to reproduce VoxelRCNN+3d_dual_fusion. The error message is as follows:

RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters that were not used in producing loss. You can enable unused parameter detection by (1) passing the keyword argument `find_unused_parameters=True` to `torch.nn.parallel.DistributedDataParallel`; (2) making sure all `forward` function outputs participate in calculating loss. If you already have done the above two steps, then the distributed data parallel module wasn't able to locate the output tensors in the return value of your module's `forward` function. Please include the loss function and the structure of the return value of `forward` of your module when reporting this issue (e.g. list, dict, iterable).

Could you clarify whether SemDeepLabV3 model does not participate in gradient updates during training? I noticed the following configurations in your code:

self.seg_loss = model_cfg.get("SEG_LOSS", False)
self.aux_pts_loss = model_cfg.get("AUX_PTS_LOSS", False)
self.aux_cns_loss = model_cfg.get("AUX_CNS_LOSS", False)

Your response would be greatly appreciated!