meicrs / gdsrec Goto Github PK

python main.py
Namespace(dataset_path='datasets/Ciao/', data='Ciao', sigma='0', batch_size=128, embed_dim=256, epoch=100, lr=0.0001, lr_dc=0.1, lr_dc_step=1, test=False)
cuda
Loading data...
0%| | 0/100 [00:00<?, ?it/s]C:\ProgramData\Anaconda3\lib\site-packages\torch\optim\lr_scheduler.py:131: UserWarning: Detected call of lr_scheduler.step() before optimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step() before lr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
warnings.warn("Detected call of lr_scheduler.step() before optimizer.step(). "
C:\ProgramData\Anaconda3\lib\site-packages\torch\optim\lr_scheduler.py:156: UserWarning: The epoch parameter in scheduler.step() was not necessary and is being deprecated where possible. Please use scheduler.step() to step the scheduler. During the deprecation, if epoch is different from None, the closed form is used instead of the new chainable form, where available. Please open an issue if you are unable to replicate your use case: https://github.com/pytorch/pytorch/issues/new/choose.
warnings.warn(EPOCH_DEPRECATION_WARNING, UserWarning)
[TRAIN] epoch 1/100 batch loss: 0.7422 (avg 0.7422) (62.08 im/s) | 0/1328 [00:00<?, ?it/s]
[TRAIN] epoch 1/100 batch loss: 0.5316 (avg 0.5331) (1947.79 im/s) | 100/1328 [00:07<01:08, 17.83it/s]
[TRAIN] epoch 1/100 batch loss: 0.4273 (avg 0.5300) (1944.25 im/s) | 200/1328 [00:13<01:04, 17.55it/s]
[TRAIN] epoch 1/100 batch loss: 0.4054 (avg 0.5257) (2648.89 im/s) | 300/1328 [00:19<00:56, 18.32it/s]
[TRAIN] epoch 1/100 batch loss: 0.5263 (avg 0.5277) (1997.80 im/s) | 400/1328 [00:24<00:52, 17.66it/s]
[TRAIN] epoch 1/100 batch loss: 0.5789 (avg 0.5288) (1751.02 im/s) | 500/1328 [00:30<00:47, 17.42it/s]
[TRAIN] epoch 1/100 batch loss: 0.3866 (avg 0.5259) (2046.72 im/s)██▏ | 599/1328 [00:36<00:43, 16.86it/s]
[TRAIN] epoch 1/100 batch loss: 0.6647 (avg 0.5272) (1720.00 im/s)████████████▋ | 700/1328 [00:42<00:33, 18.50it/s]
[TRAIN] epoch 1/100 batch loss: 0.5163 (avg 0.5252) (2605.56 im/s)███████████████████████▏ | 800/1328 [00:47<00:29, 18.05it/s]
[TRAIN] epoch 1/100 batch loss: 0.4615 (avg 0.5227) (2012.88 im/s)█████████████████████████████████▌ | 900/1328 [00:53<00:24, 17.16it/s]
[TRAIN] epoch 1/100 batch loss: 0.4912 (avg 0.5207) (2031.22 im/s)███████████████████████████████████████████▏ | 1000/1328 [00:59<00:18, 17.82it/s]
[TRAIN] epoch 1/100 batch loss: 0.7690 (avg 0.5219) (2012.34 im/s)█████████████████████████████████████████████████████▍ | 1100/1328 [01:04<00:13, 17.39it/s]
[TRAIN] epoch 1/100 batch loss: 0.4381 (avg 0.5222) (1628.73 im/s)███████████████████████████████████████████████████████████████▋ | 1199/1328 [01:10<00:07, 18.25it/s]
[TRAIN] epoch 1/100 batch loss: 0.5525 (avg 0.5216) (1982.04 im/s)██████████████████████████████████████████████████████████████████████████ | 1300/1328 [01:16<00:01, 18.48it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1328/1328 [01:17<00:00, 17.07it/s]
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 443/443 [00:16<00:00, 26.51it/s]
DIRECTORY: ['dataloader.py', 'datasets', 'LICENSE', 'main.py', 'model.py', 'preprocess.py', 'README.md', 'requirements.txt', 'test.py', 'utils.py', 'pycache']:00, 26.54it/s]
0%| | 0/100 [01:34<?, ?it/s]
Traceback (most recent call last):
File "C:\Users\MSI GF\OneDrive\Desktop\GDSRec-main\main.py", line 195, in
main()
File "C:\Users\MSI GF\OneDrive\Desktop\GDSRec-main\main.py", line 119, in main
torch.save(ckpt_dict, args.data+'/latest_checkpoint_'+args.sigma+'.pth.tar')
File "C:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 377, in save
with _open_file_like(f, 'wb') as opened_file:
File "C:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 231, in _open_file_like
return _open_file(name_or_buffer, mode)
File "C:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 212, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'Ciao/latest_checkpoint_0.pth.tar'

Hello. Thank you for your excellent repository. I ran this code in Google Colab, and it gave the following error. I appreciate your help in solving my problem.

Traceback (most recent call last):
File "/content/GDSRec/main.py", line 195, in
main()
File "/content/GDSRec/main.py", line 119, in main
torch.save(ckpt_dict, args.data+'/latest_checkpoint_'+args.sigma+'.pth.tar')
File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 618, in save
with _open_zipfile_writer(f) as opened_zipfile:
File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 492, in _open_zipfile_writer
return container(name_or_buffer)
File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 463, in init
super().init(torch._C.PyTorchFileWriter(self.name))
RuntimeError: Parent directory Ciao does not exist.

作者您好，我在复现您的工作的时候，在默认参数的设置下跑出来的实验结果并没有达到论文报告的最佳值。请问是否超参数设置的问题呢？希望您能告知一下最佳实验效果的具体参数设置，如学习率、batch size、嵌入维度等。谢谢！