All Katas - ML Katas

Advanced Indexing with `gather` for NLP

this month medium (<30 mins) | NLP gather indexing

In Natural Language Processing, it's common to work with sequences of varying lengths. A frequent task is to extract the activations of the last token in each sequence from a tensor of shape...

Sparse Updates with `scatter_add_`

this month medium (<30 mins) | scatter_add sparse

In graph neural networks and other sparse data applications, you often need to update a tensor based on sparse indices. Your exercise is to implement a function that takes a tensor of `values`, a...

Selecting RoIs (Regions of Interest) with `index_select`

this month medium (<30 mins) | vision index_select

In object detection tasks, after a region proposal network (RPN) suggests potential object locations, these regions of interest (RoIs) need to be extracted from the feature map for further...

Replicating `torch.nn.Embedding` with `gather`

this month medium (<30 mins) | embeddings NLP gather

The `torch.nn.Embedding` layer is fundamental in many deep learning models, especially in NLP. Your task is to replicate its forward pass functionality using `torch.gather`. You'll create a...