search

tum-vision / tandem

[CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo
912 stars 146 forks source link

TypeError when train CVA-MVSNet #31

Open ddyj opened 2 years ago

ddyj commented 2 years ago

Thank you for sharing this great paper and excellent code. I followed the README file in CVA-MVSNet. When I tried to train the model, there was a TypeError. Could you please help me? Thank you for your time.

Traceback (most recent call last): File "train.py", line 127, in main(*parse_args(parser)) File "train.py", line 123, in main trainer.fit(model) File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 859, in fit self.single_gpu_train(model) File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/pytorch_lightning/trainer/distrib_parts.py", line 503, in single_gpu_train self.run_pretrain_routine(model) File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1015, in run_pretrain_routine self.train() File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 347, in train self.run_training_epoch() File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 405, in run_training_epoch for batch_idx, (batch, is_last_batch) in self.profiler.profile_iterable( File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/pytorch_lightning/profiler/profilers.py", line 64, in profile_iterable value = next(iterator) File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 801, in _with_is_last last = next(it) File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 561, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/media/dai/NEWSMY/depth_estimate/tandem-master/cva_mvsnet/models/datasets.py", line 583, in getitem item = self.dataset.getitem(idx) File "/media/dai/NEWSMY/depth_estimate/tandem-master/cva_mvsnet/models/datasets.py", line 562, in getitem data = self.transform(data) File "/media/dai/NEWSMY/depth_estimate/tandem-master/cva_mvsnet/models/datasets.py", line 97, in preprocess img_aug = color_trans(img_ori) File "/media/dai/NEWSMY/anaconda3/envs/sfm/lib/python3.8/site-packages/torchvision/transforms/transforms.py", line 61, in call img = t(img) TypeError: 'tuple' object is not callable