An error that shouldn't have occurred

[littleblackzi]

I completely understand the meaning of this code, but it reported an error, when I changed data = data[:, :, 0] to data = data[:, :], the error was gone.But I know I can't change it that way.

Log as follows：
/home/oem/anaconda3/envs/interfuser/lib/python3.7/site-packages/torch/distributed/launch.py:188: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects --local_rank argument to be set, please
change it to read from os.environ['LOCAL_RANK'] instead. See
https://pytorch.org/docs/stable/distributed.html#launch-utility for
further instructions

FutureWarning,
Training with a single process on 1 GPUs.
Loading pretrained weights from url (https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet50d_ra2-464e36ba.pth)
Model interfuser_baseline created, param count:52935567
Data processing configuration for current model + dataset:
input_size: (3, 224, 224)
interpolation: bicubic
mean: (0.485, 0.456, 0.406)
std: (0.229, 0.224, 0.225)
crop_pct: 0.875
CNN backbone and transformer blocks using different learning rates!
165 weights in the cnn backbone, 274 weights in other modules
AMP not enabled. Training in float32.
Scheduled epochs: 35
Sub route dir nums: 1628
Sub route dir nums: 73
Traceback (most recent call last):
File "train.py", line 1831, in
main()
File "train.py", line 1241, in main
mixup_fn=mixup_fn,
File "train.py", line 1339, in train_one_epoch
for batch_idx, (input, target) in enumerate(loader):
File "/home/oem/anaconda3/envs/interfuser/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 628, in next
data = self._next_data()
File "/home/oem/anaconda3/envs/interfuser/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1333, in _next_data
return self._process_data(data)
File "/home/oem/anaconda3/envs/interfuser/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1359, in _process_data
data.reraise()
File "/home/oem/anaconda3/envs/interfuser/lib/python3.7/site-packages/torch/_utils.py", line 543, in reraise
raise exception
IndexError: Caught IndexError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/oem/anaconda3/envs/interfuser/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
data = fetcher.fetch(index)
File "/home/oem/anaconda3/envs/interfuser/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 58, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/oem/anaconda3/envs/interfuser/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 58, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/oem/InterFuser/interfuser/timm/data/carla_dataset.py", line 312, in getitem
seg_image = self.seg_transform(seg_image)
File "/home/oem/anaconda3/envs/interfuser/lib/python3.7/site-packages/torchvision/transforms/transforms.py", line 95, in call
img = t(img)
File "/home/oem/InterFuser/interfuser/timm/data/transforms_carla_factory.py", line 44, in call
data = data[:, :, 0]
IndexError: too many indices for array
Do you have any suggestions about this？

[deepcs233]

Hi!

In the released code, we didn't involve the segmentation input. So we didn't check the related code and function. Can you print the shape of data? If data is a 2D array, I think the removal of the last 0 is fine.

File "/home/oem/InterFuser/interfuser/timm/data/transforms_carla_factory.py", line 44, in call
data = data[:, :, 0]