Homework 4
Aggregazione dei criteri
P.S. I increased the number of files to upload from 1 to 5, so if you want you may include up to 4 local image files in your solution.
Aperto: giovedì, 25 marzo 2021, 00:00
Data limite: giovedì, 8 aprile 2021, 00:00
Instructions:
As always, please provide your solution in a Jupyter Notebook.
- Now that you have all the tools to train an MLP with high performance on MNIST, try reaching 0-loss (or 100% accuracy) on the training data (with a small epsilon, e.g. 99.99% training performance -- don't worry if you overfit!). The implementation is completely up to you. You just need to keep it an MLP without using fancy layers (e.g., keep the
Linearlayers, don't useConv1dor something like this, don't use attention). You are free to use any LR scheduler or optimizer, any one of batchnorm/groupnorm, regularization methods... If you use something we haven't seen during lectures, please motivate your choice and explain (as briefly as possible) how it works. - Try reaching 0-loss on the training data with permuted labels. Assess the model on the test data (without permuted labels) and comment. Help yourself with 3. Tip: To permute the labels, act on the
trainset.targetswith an appropriate torch function. Then, you can pass this "permuted"Datasetto aDataLoaderlike so:trainloader_permuted = torch.utils.data.DataLoader(trainset_permuted, batch_size=batch_size_train, shuffle=True). You can now use thisDataLoaderinside the training function. Additional view for motivating this exercise:.