Reference no: EM132499655

Complete experiment using python and pytorch library. Wite a report in word 20 pages on how to get the results step by step. Together with coding program. And presentation 30 slides to show results and future improvement. You can follow attached example format for titanic report and slides.

Suggest to design the experiment as follows:

Step 1. Define a shallow VGG-like network
say a VGG with 3 or 4 Conv layers without Batch Normalization. This is easy for debugging.

Step 2. Train this shallow VGG baseline network on CIFAR-10, generate Top-1 accuracy, refer to
Step 3. Run Automated Gradual Pruner (AGP) Pruning on this shallow VGG, to prune network weights during retraining and generate Top-1 accuracy.

Step 1 - 3 is the baseline of network pruning in the spatial domain. Next, extend to pruning in the frequency domain:
Step 4. refer to the frequency domain pruning paper (figure 1), transform the shallow VGG network pre-trained at Step 2 to the frequency domain, and test the Top-1 accuracy. It should report the same accuracy as in Step 2

Step 5. refer to Section 2.2 in the paper, prune the frequency-domain coefficients generated at Step 4, with different manually chosen thresholds, and test the Top-1 accuracy again with the pruned network, observe how does the performance change. For debug purposes, you can prune Conv layer by layer.

You can compare the compression ratio and accuracy, between Step 5 and Step 3. The comparisons can verify whether Step 4 and 5 are correct or not, to some extent.

The final step, integrate the frequency-domain pruning with AGP training.

Step 6. implement the update rule as referred to Section 2.4 in the paper with the AGP training code (Step 3), and perform frequency-domain pruning during training.

Attachment:- co-design.rar