search

tsunghan-wu / RandLA-Net-pytorch

:four_leaf_clover: Pytorch Implementation of RandLA-Net (https://arxiv.org/abs/1911.11236)
MIT License
122 stars 33 forks source link

problem about train #20

Closed Dreameo closed 1 year ago

Dreameo commented 2 years ago

I got a bug when I training

(randlanet) wx@dl-group-workstation:/media/wx/HDD/DQ/RandLA-Net-pytorch-main$ python train_SemanticKITTI.py 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 19130/19130 [00:40<00:00, 473.39it/s] 0%| | 0/3826 [00:03<?, ?it/s] Traceback (most recent call last): File "train_SemanticKITTI.py", line 191, in main() File "train_SemanticKITTI.py", line 187, in main trainer.train() File "train_SemanticKITTI.py", line 131, in train self.train_one_epoch() File "train_SemanticKITTI.py", line 120, in train_one_epoch loss, end_points = compute_loss(end_points, self.train_dataset, self.criterion) File "/media/wx/HDD/DQ/RandLA-Net-pytorch-main/network/loss_func.py", line 28, in compute_loss loss = criterion(valid_logits, valid_labels).mean() File "/home/wx/anaconda3/envs/randlanet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/wx/anaconda3/envs/randlanet/lib/python3.6/site-packages/torch/nn/modules/loss.py", line 1152, in forward label_smoothing=self.label_smoothing) File "/home/wx/anaconda3/envs/randlanet/lib/python3.6/site-packages/torch/nn/functional.py", line 2846, in cross_entropy return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing) RuntimeError: weight tensor should be defined either for all 19 classes or no classes but got weight tensor of shape: [1, 19]

could you please help me？

LeongVan commented 2 years ago

I've got the same question. Have you solved it yet?

francisx2019 commented 1 year ago

I've got the same question. Have you solved it yet?

mzyCSDN commented 1 year ago

I got a bug when I training

(randlanet) wx@dl-group-workstation:/media/wx/HDD/DQ/RandLA-Net-pytorch-main$ python train_SemanticKITTI.py 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 19130/19130 [00:40<00:00, 473.39it/s] 0%| | 0/3826 [00:03<?, ?it/s] Traceback (most recent call last): File "train_SemanticKITTI.py", line 191, in main() File "train_SemanticKITTI.py", line 187, in main trainer.train() File "train_SemanticKITTI.py", line 131, in train self.train_one_epoch() File "train_SemanticKITTI.py", line 120, in train_one_epoch loss, end_points = compute_loss(end_points, self.train_dataset, self.criterion) File "/media/wx/HDD/DQ/RandLA-Net-pytorch-main/network/loss_func.py", line 28, in compute_loss loss = criterion(valid_logits, valid_labels).mean() File "/home/wx/anaconda3/envs/randlanet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/wx/anaconda3/envs/randlanet/lib/python3.6/site-packages/torch/nn/modules/loss.py", line 1152, in forward label_smoothing=self.label_smoothing) File "/home/wx/anaconda3/envs/randlanet/lib/python3.6/site-packages/torch/nn/functional.py", line 2846, in cross_entropy return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing) RuntimeError: weight tensor should be defined either for all 19 classes or no classes but got weight tensor of shape: [1, 19]

could you please help me？

I had got the same question,but i had solved it . Modify the "train_SemanticKITTI.py" . `

m--------'class_weights' arguments add '.latten()'-----------------

    # Loss Function
    class_weights = torch.from_numpy(train_dataset.get_class_weight()).float().cuda().latten()
    self.criterion = nn.CrossEntropyLoss(weight=class_weights, reduction='none')`
mzyCSDN commented 1 year ago

I've got the same question. Have you solved it yet?

# Loss Function
class_weights = torch.from_numpy(train_dataset.get_class_weight()).float().cuda().latten()
self.criterion = nn.CrossEntropyLoss(weight=class_weights, reduction='none')`
mzyCSDN commented 1 year ago

I've got the same question. Have you solved it yet?

# Loss Function
class_weights = torch.from_numpy(train_dataset.get_class_weight()).float().cuda().latten()
self.criterion = nn.CrossEntropyLoss(weight=class_weights, reduction='none')`
wwxhzyy commented 1 year ago

I got a bug when I training /home/b6/anaconda3/bin/python /home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py 100%|██████████| 19130/19130 [00:28<00:00, 665.05it/s] 0%| | 0/3826 [00:01<?, ?it/s] Traceback (most recent call last): File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py", line 191, in main() File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py", line 187, in main trainer.train() File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py", line 131, in train self.train_one_epoch() File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py", line 119, in train_one_epoch end_points = self.net(batch_data) File "/home/b6/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, *kwargs) File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/network/RandLANet.py", line 51, in forward f_sampled_i = self.random_sample(f_encoder_i, end_points['sub_idx'][i]) File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/network/RandLANet.py", line 93, in random_sample pool_features = pool_features.max(dim=3, keepdim=True)[0] # batchchannelnpoints1 RuntimeError: cannot perform reduction function max on tensor with no elements because the operation does not have an identity could you please help me？

wwxhzyy commented 1 year ago

I got a bug when I training /home/b6/anaconda3/bin/python /home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py 100%|██████████| 19130/19130 [00:29<00:00, 646.68it/s] 1%| | 45/3826 [02:51<4:00:25, 3.82s/it] Traceback (most recent call last): File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py", line 191, in main() File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py", line 187, in main trainer.train() File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py", line 131, in train self.train_one_epoch() File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/train_SemanticKITTI.py", line 108, in train_one_epoch for batch_idx, batch_data in enumerate(tqdm_loader): File "/home/b6/anaconda3/lib/python3.8/site-packages/tqdm/std.py", line 1178, in iter for obj in iterable: File "/home/b6/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 435, in next data = self._next_data() File "/home/b6/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1085, in _next_data return self._process_data(data) File "/home/b6/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1111, in _process_data data.reraise() File "/home/b6/anaconda3/lib/python3.8/site-packages/torch/_utils.py", line 428, in reraise raise self.exc_type(msg) ValueError: Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/b6/anaconda3/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop data = fetcher.fetch(index) File "/home/b6/anaconda3/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/b6/anaconda3/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/dataset/semkitti_trainset.py", line 36, in getitem selected_pc, selected_labels, selected_idx, cloud_ind = self.spatially_regular_gen(item, self.data_list) File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/dataset/semkitti_trainset.py", line 46, in spatially_regular_gen selected_pc, selected_labels, selected_idx = self.crop_pc(pc, labels, tree, pick_idx) File "/home/b6/ww/KITTI(semantic)/KITTI(semantic)/L5 RandLA-Net-pytorch-main/L5 RandLA-Net-pytorch-main/RandLA-Net-pytorch-main/dataset/semkitti_trainset.py", line 68, in crop_pc select_idx = search_tree.query(center_point, k=cfg.num_points)[1][0] File "sklearn/neighbors/_binary_tree.pxi", line 1342, in sklearn.neighbors._kd_tree.BinaryTree.query ValueError: k must be less than or equal to the number of training points

Process finished with exit code 1 could you please help me？

hanm2019 commented 1 year ago

I've got the same question. Have you solved it yet?

# Loss Function
class_weights = torch.from_numpy(train_dataset.get_class_weight()).float().cuda().latten()
self.criterion = nn.CrossEntropyLoss(weight=class_weights, reduction='none')`

do you mean flatten() ?