TypeError when train CVA-MVSNet

[YuhsiHu]

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.

GPU available: True, used: True
INFO:lightning:GPU available: True, used: True
No environment variable for node rank defined. Set as 0.
WARNING:lightning:No environment variable for node rank defined. Set as 0.
CUDA_VISIBLE_DEVICES: [0]
INFO:lightning:CUDA_VISIBLE_DEVICES: [0]
Validation sanity check: 0it [00:00, ?it/s]/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Epoch 1: 0%| | 0/2714 [00:00<?, ?it/s]Traceback (most recent call last):
File "train.py", line 126, in
main(*parse_args(parser))
File "train.py", line 122, in main
trainer.fit(model)
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py", line 859, in fit
self.single_gpu_train(model)
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/pytorch_lightning/trainer/distrib_parts.py", line 503, in single_gpu_train
self.run_pretrain_routine(model)
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py", line 1015, in run_pretrain_routine
self.train()
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/pytorch_lightning/trainer/training_loop.py", line 347, in train
self.run_training_epoch()
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/pytorch_lightning/trainer/training_loop.py", line 406, in run_training_epoch
enumerate(_with_is_last(train_dataloader)), "get_train_batch"
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/pytorch_lightning/profiler/profilers.py", line 64, in profile_iterable
value = next(iterator)
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/pytorch_lightning/trainer/training_loop.py", line 801, in _with_is_last
last = next(it)
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 530, in next
data = self._next_data()
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1224, in _next_data
return self._process_data(data)
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1250, in _process_data
data.reraise()
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/torch/_utils.py", line 457, in reraise
raise exception
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/hyx/tandem/cva_mvsnet/models/datasets.py", line 583, in getitem
item = self.dataset.getitem(idx)
File "/home/hyx/tandem/cva_mvsnet/models/datasets.py", line 562, in getitem
data = self.transform(data)
File "/home/hyx/tandem/cva_mvsnet/models/datasets.py", line 97, in preprocess
img_aug = color_trans(img_ori)
File "/home/hyx/anaconda3/envs/tandem/lib/python3.7/site-packages/torchvision/transforms/transforms.py", line 95, in call
img = t(img)
TypeError: 'tuple' object is not callable

[ddyj]

Did you solve this problem, I have this problem too

[YuhsiHu]

No, I didn't.

[wyt1004]

I guess this may be caused by different pytorch versions.
The transforms.ColorJitter.get_params function in datasets.py returns a tuple, and the tuple cannot be called as a function in the transforms.Compose function.
I tried a working method, modifying datasets.py:

fn_idx, brightness_factor, contrast_factor, saturation_factor, hue_factor = transforms.ColorJitter.get_params(
brightness=brightness,
contrast=contrast,
saturation=saturation,
hue=hue
)
color_trans = transforms.Compose([
transforms.ToPILImage(),
transforms.ColorJitter(brightness=brightness_factor,
contrast=contrast_factor,
saturation=saturation_factor),
])
Hope this helps you.