ML Katas

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...

In computer vision, a common operation is to extract patches from an image. Your task is to write a function that extracts a patch of a given size from a specific starting location in an image...

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...

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...

In domain adaptation, you might need to map labels from a source domain to a target domain. Imagine you have a set of labels and a mapping that specifies how each old label corresponds to a new...

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...