-
Notifications
You must be signed in to change notification settings - Fork 9.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
alexnet [with cifar-10, batch size 256, worker 6]. training loss: NAN #152
Comments
@Foristkirito Could you provide a small snippet to reproduce your bug? |
@wangg12 of course, I just use the modified code by me.
|
@wangg12 I figure it out. I made a mistake. Problem solved thank you guy. |
@Foristkirito What is the problem? |
@wangg12 the problem is directories. It's necessary to maintain the project directory structure and put it right at your home directory. I do not understand why but it does not work if you put |
@Foristkirito Do you get better results with alexnet on cifar-10 now? Also IMO, alexnet is not suitable for cifar10 though. The architecture is for bigger images but 32x32 cifar-10 images. Besides, if you do not use pre-trained weights, you should be careful with the learning rate and the weights initialization (The random behavior can be fixed by torch.manual_seed(seed)). |
@wangg12 The accuracy of |
No description provided.
The text was updated successfully, but these errors were encountered: