Open timthegod opened 5 years ago
I have the same problem,how did solve it?
Can you share the environment with me! I face some bug that i can't start training!
D:\Project_venv\two-stream-fusion-for-action-recognition-in-videos-master\lib\site-packages\torch\optim\lr_scheduler.py:82: 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
"https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning)
Traceback (most recent call last):
File "conv_fusion.py", line 347, in
thanks!!
Hi, timthegod!
I met this problem,
The videoname variable is not defined. https://github.com/tomar840/two-stream-fusion-for-action-recognition-in-videos/blob/master/dataloader/split_train_test_video.py#L50
Could tell me how to slove?
I fixed some bug and start training. How can I test it? And how to train our own model using own data? Thank you!