Robert Bunn

What to do about large models that won't fit into a layer?

2

Is it possible to use an S3 bucket when the model won't fit directly into a lambda layer? Resnet18 is quite small and not typical of DL models these days.

Is this project still active?

1

Just curious if this project will continue going forward?

Validate with Existing Model Trained on Both Classes

4

This is really great work! I noticed you appear to be using this code for creating new examples of pathology images. I am doing something similar, just not pathology. Let's...

Confusion about visualizations

3

I have found your work to be very fascinating, especially the potential for much better visualizations of what has been learned by the network. I was playing around with the...

Changing cuda to True seems to cause the code to stop working correctly

2

This project is really great work! However, I seem to be struggling trying to get it to work using cuda. First if you change cuda to True, then there is...

What is iam:GetRole?

2

> If you are running locally, make sure that the account you are running this notebook under has all of the necessary permissions: S3ReadOnlyAccess, SagemakerFullAccess, iam:GetRole, and ECRFullAccess What is...

Baffling Error

2

This is the end of my output when I run pytorch_lightning_regression.py without changes. I can't seem to figure out what is wrong or how to fix it. TEST RESULTS {'test_loss':...

Hello, Looks like this might be some great stuff! How do you set up the data to run this code on either the apofretin data, MRI or something similar (not...