Blogs and Posts

“🚀 Curious about PyTorch 2.0? Dive into its game-changing features like torch.compile, TorchDynamo, and AoTAutograd! Learn how PyTorch blends eager execution & graph mode for faster, seamless model training. 🧵👇 [Read More]

Recently there have been many works applying diffusion models to NLP domain, they majorly take two approaches, either they alter the diffusion process a little to make the noising and denoising steps possible for discrete data, or the second approach is to convert the discrete text data into a continuous... [Read More]

This tutorial is a brief introduction on how you can train a machine translation model (or any other seq2seq model) using PyTorch Ignite. This notebook uses Models, Dataset and Tokenizers from Huggingface, hence they can be easily replaced by other models from the 🤗 Hub. Further, it allows you to... [Read More]

Skin Segmentation can be a important aspect of pre-processing data for Deep Learning Models. It can be used whenever you are making a model which works on Hands, Faces etc. Unlike segmentation in other tasks (like this or this ) here it can be done without using a huge DL... [Read More]

BART Paper - BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension [Read More]