How to use this project

[hahahaha2019310241]

Hello, I am very interested in your project, but I do not know how to run this project on my own data set. May I ask how to use this project. Thank you!

[lmaxwell]

Could you please give me more details about your goals? Are you looking to pretrain a self-supervised model with your own data set, or are you interested in fine-tuning a pre-trained model on your data? I'd be happy to assist you in getting started with the project.

[hahahaha2019310241]

Thank you very much for your reply. I want to reproduce the results of the atst model on the us8k data set, but I now have the following problems, how to solve this, thank you very much!
Take key teacher in provided checkpoint dict
Pretrained weights found at /home/lxz/PycharmProjects/lxz/project/audiossl-main/audiossl/methods/atst/base.ckpt and loaded with msg: _IncompatibleKeys(missing_keys=[], unexpected_keys=['head.0.weight', 'head.1.weight', 'head.1.bias', 'head.1.running_mean', 'head.1.running_var', 'head.1.num_batches_tracked', 'head.3.weight'])
Traceback (most recent call last):
File "/home/lxz/PycharmProjects/lxz/project/audiossl-main/audiossl/methods/atst/shell/downtream/finetune/../../../downstream/train_finetune.py", line 201, in
main()
File "/home/lxz/PycharmProjects/lxz/project/audiossl-main/audiossl/methods/atst/shell/downtream/finetune/../../../downstream/train_finetune.py", line 195, in main
run_n_folds(args, pretrained_module, num_folds)
File "/home/lxz/PycharmProjects/lxz/project/audiossl-main/audiossl/methods/atst/shell/downtream/finetune/../../../downstream/train_finetune.py", line 157, in run_n_folds
test_metrics.append(run(args, deepcopy(pretrained_module), fold+1))
File "/home/lxz/PycharmProjects/lxz/project/audiossl-main/audiossl/methods/atst/shell/downtream/finetune/../../../downstream/train_finetune.py", line 124, in run
trainer: Trainer = Trainer(
File "/home/lxz/anaconda3/envs/audiossl/lib/python3.10/site-packages/pytorch_lightning/utilities/argparse.py", line 70, in insert_env_defaults
return fn(self, **kwargs)
File "/home/lxz/anaconda3/envs/audiossl/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 401, in init
self._accelerator_connector = _AcceleratorConnector(
File "/home/lxz/anaconda3/envs/audiossl/lib/python3.10/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py", line 147, in init
self._accelerator_flag = self._choose_gpu_accelerator_backend()
File "/home/lxz/anaconda3/envs/audiossl/lib/python3.10/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py", line 367, in _choose_gpu_accelerator_backend
raise MisconfigurationException("No supported gpu backend found!")
lightning_fabric.utilities.exceptions.MisconfigurationException: No supported gpu backend found!

[lmaxwell]

Did you have torch installed with cuda support ? Could you please check what the following code returns ?

print(torch.cuda.is_available())