Introduction
In this project, you will explore the use of k-fold Cross-validation test image gradients by applying it on the following three tasks:
o Determine the best 2-layer MLP structure.
o Class Visualization: “Deep Inside Convolutional Networks: Visualising Image
Classification Models and Saliency Maps” and “Understanding Neural Networks
Through Deep Visualization”
o Style Transfer: “Image style transfer using convolutional neural networks”
Please go through the above reference papers very carefully. You are expected to understand how to accomplish each task using the methods presented in the papers and write code to implement them by completing Project1.ipynb which is available in Project1.zip from LumiNUS.
Please take careful note of the following (failure to do so could incur penalties):
o Your code MUST be kept within “TODO” and “END OF YOUR CODE”;
o Do NOT modify the definitions of the functions in Project1.ipynb;
o Write “clean” (easily readable) code and check to make sure it runs/executes;
o Do NOT share your solution code with others; submit your own work/code; there
will be penalties for cheating and late submission. Project#1 submission (Deadline: 6PM, Saturday 6 March 2021)
- Export your notebook file Project1.ipynb to an html page and include it in the Project1 folder. Please make sure that the submitted notebooks have been run and the cell outputs are visible.
- Compress the Project1 folder into a zip file and rename it as follows before uploading it to LumiNUS: “YourStudentNumber_Project1.zip”.
