Should I use softmax as output when using cross entropy loss in pytorch? Should I use softmax as output when using cross entropy loss in pytorch? python python

Should I use softmax as output when using cross entropy loss in pytorch?


python pytorch mnist softmax

As stated in the torch.nn.CrossEntropyLoss() doc:

This criterion combines nn.LogSoftmax() and nn.NLLLoss() in one single class.

Therefore, you should not use softmax before.

Recent Posts
How can I color dots in a xy scatterplot according to column value?
How to update a claim in ASP.NET Identity?
What does {0} mean when initializing an object?
Accessing members of items in a JSONArray with Java
How to log SQL statements in Spring Boot?
Powershell Get-WebSite name parameter is ignored
How to detect scroll to bottom of html element
Java synchronized method
How to test controllers with CodeIgniter?
Detect Visual Composer
Matplotlib: Specify format of floats for tick labels
Rails join a list of strings with commas and "and" before the last