Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit

Image Classification with CNN

In this project, we will do image classification using the Fashion MNIST dataset. The lab    “ COMP338_Lab_08_Fashion_MNIST_Classification.ipynb” on Canvas shows the example source code for this assignment.

Tasks:

1. (30 marks) Design a deep neural network for image classification.

2. (30 marks) Train and test your network on Fashion MNIST dataset.

3. (40 marks) Write a report to clearly explain your network, the intuition behind your design, and discussion of your results.

Rules:

-    You can refer to any papers and reuse any source code. However, you should clearly cite the references in your report.

-    Use free Google Colab account (https://colab.research.google.com/) for training. The maximum training time on a free Google Colab account is 12 hours.

Our solution will be evaluated by:

-    The design concept or novelty of your network design (30%).

-    The accuracy of your trained model, compared with other students (30%).

-    The completeness of your report (40%).