Demo Code

Download the demo code Here

Task

Follow the Pytorch tutorial TRAINING A CLASSIFIER to write the image classifier. Feel free to copy the code into vscode block by block when going thru the tutorial. At the end, you should have a runnable code.

To improve the performance, please try to tune the hyperparameters. The tunable hyperparameters includes not limited to (in the order of importance):

• Network Architecture
  • CNN output channels
  • Number of layers
• Batch size
• Optimizer
• Learning rate
• Epoch number
• Activation functions

Hint: The primary reason of the low accuracy result in the current setup is the weak expression capacity of the model (i.e., the model is too simple).

Write Report

In addition to the program output, you need to include the following items in your report:

• The final result (in program output)
• What changes you made
• Lessons learned from tunning this model:
  • What are important v.s. unimportant in deep learning?

Deliverables and Rubrics

Overall, you need to complete the environment installation and be able to run the demo code. You need to submit:

• (50 pts) A PDF from running the your code in jupyter notebook with accuracy reported in the program output.
• (50 pts) The rest of 50 pts is decided by your performance:

Criterion

The goal is to increase the accuracy above the baseline 54%.