{"full_name":"labmlai/annotated_deep_learning_paper_implementations","owner":"labmlai","name":"annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","description":"🧑‍🏫 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, ... 🧠","homepage":"https://nn.labml.ai","topics":[],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/64068543?v=4","created_at":"2020-08-25T02:29:34Z","pushed_at":"2026-11-02T05:57:43Z","metrics":{"stars":67742,"forks":6789,"watchers":496,"issues":145,"prs":155,"releases":0,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":11},"growth":{"day":{"stars":12,"forks":0,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10"],"stars":[67730,67742],"forks":[6789,6789],"watchers":[496,496],"issues_open":[null,null],"prs_open":[null,null]},"boards":{},"same_owner":[],"issues":[{"number":275,"title":"How to Contribute to This Repository","comments":8,"created_at":"2024-09-15T08:51:24Z"},{"number":270,"title":"Unet error in DDPM","comments":4,"created_at":"2024-08-14T07:17:27Z"},{"number":195,"title":"Training code or references for training the latent diffusion model on a custom dataset","comments":3,"created_at":"2023-07-08T02:37:11Z"},{"number":169,"title":"Dimension of subsequent layers in Hypernetwork","comments":3,"created_at":"2023-02-27T23:49:52Z"},{"number":165,"title":"Missing activation for the time embedding inside ResidualBlock for DDPM?","comments":3,"created_at":"2023-01-30T10:08:50Z"},{"number":107,"title":"[BUG] StyleGAN2: latent vector is ignored","comments":3,"created_at":"2022-02-07T10:31:48Z"},{"number":260,"title":"How to use my own database for training and evaluating Retro for Question-Answering?","comments":2,"created_at":"2024-06-27T03:34:39Z"},{"number":180,"title":"MultiHeadAttention  parameter  setting","comments":2,"created_at":"2023-04-30T09:25:31Z"}],"discussions":[{"number":295,"title":"The SGR Manifold: Surpassing Transformer Efficiency via Singular Geometric Strikes","comments":0,"category":"Ideas","created_at":"2026-01-21T00:08:35Z"},{"number":279,"title":"Wanted help to understand how I can effectively use LabMl","comments":1,"category":"General","created_at":"2024-12-06T06:59:36Z"},{"number":277,"title":"Questions re: the DeepNorm implementation","comments":0,"category":"Q&A","created_at":"2024-11-14T12:32:14Z"},{"number":269,"title":"Interested to Contribute","comments":0,"category":"Show and tell","created_at":"2024-08-10T18:42:10Z"},{"number":248,"title":"[pip install labml-nn] showed warnings and when run image_to_image.py it showed: [ModuleNotFoundError: No module named 'transformers']","comments":1,"category":"General","created_at":"2024-03-21T19:15:39Z"},{"number":183,"title":"PPO experiment on colab report an error","comments":2,"category":"Q&A","created_at":"2023-05-14T09:41:50Z"},{"number":181,"title":"Any tools to render side-by-side annotations from source code?","comments":1,"category":"General","created_at":"2023-05-08T00:49:36Z"},{"number":176,"title":"Can I generate nn.labml.ai type of interface for my own notebooks?","comments":0,"category":"General","created_at":"2023-04-05T16:54:12Z"}],"latest_release":null,"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}