Facing Challenges with CNN Training

Hello

Facing an Issue with Convolutional Neural Network Training.
I’ve been facing a perplexing issue while training a convolutional neural network (CNN) for image classification. Even after following best practices and ensuring data preprocessing, I consistently encounter a sudden increase in loss during training, leading to degraded performance.

I’ve already checked my network architecture, optimizer settings, and data pipeline, but the problem exist. Any suggestions on this issue would be greatly appreciated.

Thank you!

Thank you
stevediaz

Since this is not a course related assignment, why don’t you post a link to the notebook / upload it here for others to look?