def issue: rotation_with_mask

[Wadha-Almattar]

Command: python main.py --n-gpus 1 --num-workers 5 --arch ViT-S-p16 --batch-size 128 --epochs 10 --warmup-epochs 2 - -data-index /home/guser1/SSiT/data_index/pretraining_dataset.pkl --save-path /home/guser1/SSiT/checkpoints

The code generate this error, which is coming from this function [rotation_with_mask]:

Single GPU mode

=============================== Number of training samples: 999

Total Epochs:

10

current Epochs No:

0 0it [00:00, ?it/s] Traceback (most recent call last): File "main.py", line 140, in main() File "main.py", line 88, in main worker(0, n_gpus, args) File "main.py", line 121, in worker train( File "/home/guser1/SSiT/train.py", line 41, in train for step, train_data in progress: File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/tqdm/std.py", line 1195, in iter for obj in iterable: File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 633, in next data = self._next_data() File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1345, in _next_data return self._process_data(data) File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data data.reraise() File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/_utils.py", line 644, in reraise raise exception AttributeError: Caught AttributeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop data = fetcher.fetch(index) File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/guser1/SSiT/data.py", line 67, in getitem img_stu, img_tea, mask_stu, mask_tea = self.transform(img, mask) File "/home/guser1/SSiT/data.py", line 152, in call img_stu, mask_stu = self.rotation_with_mask(self.rotation_stu, img_stu, mask_stu, self.p_rotation_stu) File "/home/guser1/SSiT/data.py", line 185, in rotation_with_mask img = F.rotate(img, angle, tf.resample, tf.expand, tf.center, tf.fill) File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1614, in getattr raise AttributeError("'{}' object has no attribute '{}'".format( AttributeError: 'RandomRotation' object has no attribute 'resample'

[Wadha-Almattar]

When these lines is omitted from the function [rotation_with_mask] and change it as follow:

These two lines are removed: img = F.rotate(img, angle, tf.resample, tf.expand, tf.center, tf.fill) mask = F.rotate(mask, angle, tf.resample, tf.expand, tf.center, tf.fill)

Instead, I only pass two argument and the code starts training but again another error popped up at the end of the training: img = F.rotate(img, angle) mask = F.rotate(mask, angle)

[2023-06-09 12:37:05] epoch: 10/10, cl loss: 3.745282, ss loss: 0.186888, lr: 0.000001, moco_m: 0.999995: : 7it [00:04, 1.46it/s]

Saved checkpoint to /home/guser1/SSiT/checkpoints

Traceback (most recent call last): File "main.py", line 140, in main() File "main.py", line 88, in main worker(0, n_gpus, args) File "main.py", line 128, in worker torch.distributed.barrier() File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/distributed/distributed_c10d.py", line 3327, in barrier default_pg = _get_default_group() File "/home/guser1/anaconda3/envs/ssit/lib/python3.8/site-packages/torch/distributed/distributed_c10d.py", line 707, in _get_default_group raise RuntimeError( RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.

[Wadha-Almattar]

I removed this line, and it looks fine: File "main.py", line 128, in worker torch.distributed.barrier()

BUT, still trying to figure out the problem here:

function [rotation_with_mask] issue with tf.resample img = F.rotate(img, angle, tf.resample, tf.expand, tf.center, tf.fill) mask = F.rotate(mask, angle, tf.resample, tf.expand, tf.center, tf.fill)

[YijinHuang]

The parameter 'resample' for RandomRotation is removed after version 0.13 of torchvision. You can downgrade the version of torchvision to 0.12 or remove this parameter to solve this issue.