Skip to content

Conversation

@VincentSchaik
Copy link
Owner

What changes are you trying to make? (e.g. Adding or removing code, refactoring existing code, adding reports)

  • Implemented and evaluating a vision model using Keras on the Fashion MNIST dataset.
  • Evaluated a simple baseline linear model and evaluatied against a simple CNN model.
  • Included Lab 1, 2, 3.

What did you learn from the changes you have made?

  • Training and evaluating the models with the best performing configurations.

Was there another approach you were thinking about making? If so, what approach(es) were you thinking of?

  • Included in the reflections section at each stage.

Were there any challenges? If so, what issue(s) did you face? How did you overcome it?

  • Occasional crashing due to intensive operations.

How were these changes tested?

  • Conducted controlled experiments on a hyperparameter (number of filters) and a regularization technique (Dropout)
  • Generated plots and charts to visualize results.

A reference to a related issue in your repository (if applicable)

N/A

Checklist

  • I can confirm that my changes are working as intended

@VincentSchaik
Copy link
Owner Author

Completed: Assignment-1, Lab 1, 2, 3.

Copy link

@DwardEE DwardEE left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great work!

Remember, adding an activation function to your linear regression baseline model turns it into a logistic regression, not a linear one. Try removing the activation function in your model's output dense layer and rewrite the reflections.

@VincentSchaik
Copy link
Owner Author

Removed activation function to base model. Updated reflection.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants