X Transformers vs Annotated Deep Learning Paper Implementations

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Best matched with other framework tools.

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Best matched with other framework tools.