-
Notifications
You must be signed in to change notification settings - Fork 0
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
Pytorch Tutorial 5 - MNIST classification - Jupyter and Markdown #91
Conversation
Closing #66 |
I think you got the wrong folder, tutorial 5 is in |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Overall nice to read ;)
…s on copying trained weights
TODO to self:
|
…e behavior of training statistics like previewing losses and accuracy
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice addition with the anchor stuff
@dirkbrink @LRVerkin Thank you guys for the comments. I pushed changes addressing those requests, please check |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM assuming Louise is also happy
LGTM as well |
Summary
I split all the functions used in the
__main__
because the main program and argument parsing have been removed.Now the structure is linear and follows naturally from what has to be done - datasets loading, training, evaluating.
Added descriptions to steps and links to more documentation.
Changed a bit how TDQM is used.