{"id":31780639,"url":"https://github.com/ashly1991/tensorboard-mnist-tf2","last_synced_at":"2026-05-14T21:35:05.191Z","repository":{"id":316242565,"uuid":"1062561939","full_name":"Ashly1991/tensorboard-mnist-tf2","owner":"Ashly1991","description":"Visual debugging of an MNIST MLP with low-level TensorFlow 2 using tf.data + TensorBoard (scalars, histograms, images)","archived":false,"fork":false,"pushed_at":"2025-09-23T13:13:28.000Z","size":16,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-23T14:42:42.583Z","etag":null,"topics":["deep-learning","gradient-tape","jupyter-notebook","machine-learning","mnist","reproducibility","tensorboard","tensorflow","tf-data","visualization"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ashly1991.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-23T12:24:18.000Z","updated_at":"2025-09-23T13:13:32.000Z","dependencies_parsed_at":"2025-09-23T14:42:44.254Z","dependency_job_id":null,"html_url":"https://github.com/Ashly1991/tensorboard-mnist-tf2","commit_stats":null,"previous_names":["ashly1991/tensorboard-mnist-tf2"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Ashly1991/tensorboard-mnist-tf2","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ashly1991%2Ftensorboard-mnist-tf2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ashly1991%2Ftensorboard-mnist-tf2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ashly1991%2Ftensorboard-mnist-tf2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ashly1991%2Ftensorboard-mnist-tf2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ashly1991","download_url":"https://codeload.github.com/Ashly1991/tensorboard-mnist-tf2/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ashly1991%2Ftensorboard-mnist-tf2/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279003304,"owners_count":26083555,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-10T02:00:06.843Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","gradient-tape","jupyter-notebook","machine-learning","mnist","reproducibility","tensorboard","tensorflow","tf-data","visualization"],"created_at":"2025-10-10T08:16:53.382Z","updated_at":"2025-10-10T08:16:56.082Z","avatar_url":"https://github.com/Ashly1991.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Let the Tensors Board — Visual Debugging for MNIST (TensorFlow 2)\n\nThis project shows how to use **TensorBoard** to visualize and debug training of a low‑level TensorFlow 2 MLP on **MNIST**, while providing data via **`tf.data`**.\n\n## Purpose\n- Build a reproducible MNIST input pipeline with `tf.data` (shuffle → batch → repeat).\n- Train a minimal MLP using `tf.GradientTape` and manual updates.\n- Log to TensorBoard:\n  - **Scalars** (loss, accuracy, gradient norms),\n  - **Histograms** (weights/activations),\n  - **Images** (sample inputs \u0026 misclassifications),\nto diagnose common problems such as vanishing/exploding gradients, bad initialization, or incorrect activations.\n\n## Run locally\n```bash\npython -m venv .venv \u0026\u0026 source .venv/bin/activate   # Windows: .venv\\Scripts\\activate\npip install -r requirements.txt\njupyter lab let-the-tensors-board.ipynb\n```\nDuring/after training, start TensorBoard in another terminal:\n```bash\n./tb_start.sh\n# or:\ntensorboard --logdir logs --port 6006\n```\nThen open http://localhost:6006/\n\n## Notes\n- No raw datasets are committed. The notebook uses `tf.keras.datasets` to download MNIST at runtime.\n- Logs are written to `logs/`; figures can be saved to `figures/`.\n- `fails/` is provided as a placeholder directory where you can place external “failure case” scripts (not included here).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fashly1991%2Ftensorboard-mnist-tf2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fashly1991%2Ftensorboard-mnist-tf2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fashly1991%2Ftensorboard-mnist-tf2/lists"}