Hello! Thank you for your hard work in making this repository of open source code available for researchers.
I'm in the training stage for wc_vid2vid using the cityscapes dataset. I've formatted the data appropriately, successfully created the LMDB format for training, and then ran:
python -m torch.distributed.launch --nproc_per_node=1 train.py --config configs/projects/wc_vid2vid/cityscapes/seg_ampO1.yaml
However, I'm encountering the following runtime error:
/home/ubuntu/avatar/lib/python3.8/site-packages/torch/distributed/launch.py:178: 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_rankargument to be set, please change it to read fromos.environ['LOCAL_RANK']` instead. See
https://pytorch.org/docs/stable/distributed.html#launch-utility for
further instructions
warnings.warn(
Using random seed 2
Training with 1 GPUs.
Make folder logs/2022_0708_1540_06_seg_ampO1
cudnn benchmark: True
cudnn deterministic: False
Creating metadata
Traceback (most recent call last):
File "train.py", line 168, in
main()
File "train.py", line 89, in main
train_data_loader, val_data_loader = get_train_and_val_dataloader(cfg, args.seed)
File "/home/ubuntu/avatar/imaginaire/imaginaire/utils/dataset.py", line 80, in get_train_and_val_dataloader
train_dataset, val_dataset = _get_train_and_val_dataset_objects(cfg)
File "/home/ubuntu/avatar/imaginaire/imaginaire/utils/dataset.py", line 25, in _get_train_and_val_dataset_objects
train_dataset = dataset_module.Dataset(cfg, is_inference=False)
File "/home/ubuntu/avatar/imaginaire/imaginaire/datasets/paired_videos.py", line 37, in init
super(Dataset, self).init(cfg, is_inference, is_test)
File "/home/ubuntu/avatar/imaginaire/imaginaire/datasets/base.py", line 95, in init
filenames, metadata = create_metadata(
File "/home/ubuntu/avatar/imaginaire/imaginaire/utils/lmdb.py", line 148, in create_metadata
available_data_types = path.get_immediate_subdirectories(data_root)
File "/home/ubuntu/avatar/imaginaire/imaginaire/utils/path.py", line 19, in get_immediate_subdirectories
return sorted([name for name in os.listdir(input_dir)
FileNotFoundError: [Errno 2] No such file or directory: '/mnt/bigdata01/datasets/wc_vid2vid/cityscapes/train/lmdb'
`
Are there any ideas as to what is causing this error? I am currently working in a python3.8-venv because of updated dependencies (PyTorch). And if it's as simple as changing the path for the directory, where and how do I change the path?
Hello! Thank you for your hard work in making this repository of open source code available for researchers.
I'm in the training stage for wc_vid2vid using the cityscapes dataset. I've formatted the data appropriately, successfully created the LMDB format for training, and then ran:
python -m torch.distributed.launch --nproc_per_node=1 train.py --config configs/projects/wc_vid2vid/cityscapes/seg_ampO1.yaml
However, I'm encountering the following runtime error:
/home/ubuntu/avatar/lib/python3.8/site-packages/torch/distributed/launch.py:178: 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_rankargument 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 instructionswarnings.warn( Using random seed 2 Training with 1 GPUs. Make folder logs/2022_0708_1540_06_seg_ampO1 cudnn benchmark: True cudnn deterministic: False Creating metadata Traceback (most recent call last): File "train.py", line 168, in
main()
File "train.py", line 89, in main
train_data_loader, val_data_loader = get_train_and_val_dataloader(cfg, args.seed)
File "/home/ubuntu/avatar/imaginaire/imaginaire/utils/dataset.py", line 80, in get_train_and_val_dataloader
train_dataset, val_dataset = _get_train_and_val_dataset_objects(cfg)
File "/home/ubuntu/avatar/imaginaire/imaginaire/utils/dataset.py", line 25, in _get_train_and_val_dataset_objects
train_dataset = dataset_module.Dataset(cfg, is_inference=False)
File "/home/ubuntu/avatar/imaginaire/imaginaire/datasets/paired_videos.py", line 37, in init
super(Dataset, self).init(cfg, is_inference, is_test)
File "/home/ubuntu/avatar/imaginaire/imaginaire/datasets/base.py", line 95, in init
filenames, metadata = create_metadata(
File "/home/ubuntu/avatar/imaginaire/imaginaire/utils/lmdb.py", line 148, in create_metadata
available_data_types = path.get_immediate_subdirectories(data_root)
File "/home/ubuntu/avatar/imaginaire/imaginaire/utils/path.py", line 19, in get_immediate_subdirectories
return sorted([name for name in os.listdir(input_dir)
FileNotFoundError: [Errno 2] No such file or directory: '/mnt/bigdata01/datasets/wc_vid2vid/cityscapes/train/lmdb'
`
Are there any ideas as to what is causing this error? I am currently working in a python3.8-venv because of updated dependencies (PyTorch). And if it's as simple as changing the path for the directory, where and how do I change the path?
Any reply will be much appreciated!