{"id":13657344,"url":"https://github.com/tlkh/pycon-sg19-tensorflow-tutorial","last_synced_at":"2025-04-13T00:31:23.284Z","repository":{"id":87652764,"uuid":"213112649","full_name":"tlkh/pycon-sg19-tensorflow-tutorial","owner":"tlkh","description":"PyCon SG 2019 Tutorial: Optimizing TensorFlow Performance","archived":false,"fork":false,"pushed_at":"2019-11-20T14:32:03.000Z","size":1624,"stargazers_count":25,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-26T18:52:31.297Z","etag":null,"topics":["deep-learning","keras","mixed-precision","nvidia","tensorflow"],"latest_commit_sha":null,"homepage":null,"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/tlkh.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}},"created_at":"2019-10-06T05:15:44.000Z","updated_at":"2022-09-25T05:37:52.000Z","dependencies_parsed_at":null,"dependency_job_id":"41f550b2-64ff-442e-90f1-c9fed14b2123","html_url":"https://github.com/tlkh/pycon-sg19-tensorflow-tutorial","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tlkh%2Fpycon-sg19-tensorflow-tutorial","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tlkh%2Fpycon-sg19-tensorflow-tutorial/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tlkh%2Fpycon-sg19-tensorflow-tutorial/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tlkh%2Fpycon-sg19-tensorflow-tutorial/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tlkh","download_url":"https://codeload.github.com/tlkh/pycon-sg19-tensorflow-tutorial/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248650590,"owners_count":21139670,"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","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","keras","mixed-precision","nvidia","tensorflow"],"created_at":"2024-08-02T05:00:41.302Z","updated_at":"2025-04-13T00:31:22.768Z","avatar_url":"https://github.com/tlkh.png","language":"Jupyter Notebook","funding_links":[],"categories":["Optimization \u0026 Performance"],"sub_categories":[],"readme":"# PyCon SG 2019 Tutorial: Optimizing TensorFlow Performance\n\n![GitHub last commit](https://img.shields.io/github/last-commit/NVAITC/pycon-sg19-tensorflow-tutorial.svg) ![GitHub](https://img.shields.io/github/license/NVAITC/pycon-sg19-tensorflow-tutorial.svg) ![](https://img.shields.io/github/repo-size/NVAITC/pycon-sg19-tensorflow-tutorial.svg)\n\nThis workshop content covers:\n\n* a brief introduction to deep learning and TensorFlow 2.0\n* using `tf.data` and TensorFlow Datasets\n* XLA compiler and Automatic Mixed Precision (AMP)\n* speeding up CNN (ResNet-50) with XLA and AMP\n* speeding up Transformer (BERT) with XLA and AMP\n\nFor a quick guide to using Automatic Mixed Precision, check out this [TLDR](https://drive.google.com/open?id=1Nz2438DBQS591kHha2ENL7VBhmBaXQ_loQVi3rywRVU).\n\n## Content\n\n**Slides** are in this [Google Drive folder](https://drive.google.com/open?id=1RR0UhnvJ3PHL4sGRe2du4_w66Kg9KNVr).\n\n**Notebooks**\n\n| Notebook                       | Link | Solution |\n| ------------------------------ | ---- | -------- |\n| TensorFlow Dataset \u0026 tf.data   | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NVAITC/pycon-sg19-tensorflow-tutorial/blob/master/tf_dataset_demo.ipynb) |          |\n| Pet Classification with TF 2.0 | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NVAITC/pycon-sg19-tensorflow-tutorial/blob/master/tf_pet_base.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NVAITC/pycon-sg19-tensorflow-tutorial/blob/master/solutions/tf_pet_solution.ipynb) |\n| Transformers with TF 2.0       | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NVAITC/pycon-sg19-tensorflow-tutorial/blob/master/tf_transformer_base.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NVAITC/pycon-sg19-tensorflow-tutorial/blob/master/solutions/tf_transformer_solution.ipynb) |\n\nFor those running the notebooks on the workshop JupyterHub or on your own hardware, you can clone this repository.\n\n```shell\ngit clone https://github.com/NVAITC/pycon-sg19-tensorflow-tutorial\n```\n\n## Workshop Information\n\n**In-person @ PyCon SG 2019**\n\n * Attend the workshop 10am to 1pm on Saturday, October 12 at [Republic Polytechnic](https://pycon.sg/venue/).\n * Get your tickets [here](https://www.eventnook.com/event/pyconsingapore2019/).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftlkh%2Fpycon-sg19-tensorflow-tutorial","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftlkh%2Fpycon-sg19-tensorflow-tutorial","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftlkh%2Fpycon-sg19-tensorflow-tutorial/lists"}