{"id":15032348,"url":"https://github.com/the-full-stack/fsdl-text-recognizer-project","last_synced_at":"2025-05-16T06:08:10.092Z","repository":{"id":37587738,"uuid":"172592290","full_name":"the-full-stack/fsdl-text-recognizer-project","owner":"the-full-stack","description":"Lab materials for the Full Stack Deep Learning Course","archived":false,"fork":false,"pushed_at":"2022-06-14T04:25:32.000Z","size":6322,"stargazers_count":1210,"open_issues_count":15,"forks_count":427,"subscribers_count":57,"default_branch":"master","last_synced_at":"2025-05-11T18:03:34.460Z","etag":null,"topics":["deep-learning"],"latest_commit_sha":null,"homepage":"https://fullstackdeeplearning.com/course","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/the-full-stack.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-02-25T22:02:22.000Z","updated_at":"2025-05-06T17:43:52.000Z","dependencies_parsed_at":"2022-07-09T11:00:27.849Z","dependency_job_id":null,"html_url":"https://github.com/the-full-stack/fsdl-text-recognizer-project","commit_stats":null,"previous_names":["full-stack-deep-learning/fsdl-text-recognizer-project"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/the-full-stack%2Ffsdl-text-recognizer-project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/the-full-stack%2Ffsdl-text-recognizer-project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/the-full-stack%2Ffsdl-text-recognizer-project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/the-full-stack%2Ffsdl-text-recognizer-project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/the-full-stack","download_url":"https://codeload.github.com/the-full-stack/fsdl-text-recognizer-project/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254478193,"owners_count":22077676,"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"],"created_at":"2024-09-24T20:18:08.032Z","updated_at":"2025-05-16T06:08:05.037Z","avatar_url":"https://github.com/the-full-stack.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Full Stack Deep Learning Labs\n\nWelcome!\n\nProject developed during lab sessions of the [Full Stack Deep Learning Bootcamp](https://fullstackdeeplearning.com).\n\n- We will build a handwriting recognition system from scratch, and deploy it as a web service.\n- Uses Keras, but designed to be modular, hackable, and scalable\n- Provides code for training models in parallel and store evaluation in Weights \u0026 Biases\n- We will set up continuous integration system for our codebase, which will check functionality of code and evaluate the model about to be deployed.\n- We will package up the prediction system as a REST API, deployable as a Docker container.\n- We will deploy the prediction system as a serverless function to Amazon Lambda.\n- Lastly, we will set up monitoring that alerts us when the incoming data distribution changes.\n\n## Schedule for the November 2019 Bootcamp\n\n- First session (90 min)\n  - [Setup](setup.md) (10 min): Get set up with jupyterhub.\n  - Introduction to problem and [project structure](project_structure.md) (20 min).\n  - Gather handwriting data (10 min).\n  - [Lab 1](lab1.md) (20 min): Introduce EMNIST. Training code details. Train \u0026 evaluate character prediction baselines.\n  - [Lab 2](lab2.md) (30 min): Introduce EMNIST Lines. Overview of CTC loss and model architecture. Train our model on EMNIST Lines.\n- Second session (60 min)\n  - [Lab 3](lab3.md) (40 min): Weights \u0026 Biases + parallel experiments\n  - [Lab 4](lab4.md) (20 min): IAM Lines and experimentation time (hyperparameter sweeps, leave running overnight).\n- Third session (90 min)\n  - Review results from the class on W\u0026B\n  - [Lab 5](lab5.md) (45 min) Train \u0026 evaluate line detection model.\n  - [Lab 6](lab6.md) (45 min) Label handwriting data generated by the class, download and version results.\n- Fourth session (75 min)\n  - [Lab 7](lab7.md) (15 min) Add continuous integration that runs linting and tests on our codebase.\n  - [Lab 8](lab8.md) (60 min) Deploy the trained model to the web using AWS Lambda.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthe-full-stack%2Ffsdl-text-recognizer-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthe-full-stack%2Ffsdl-text-recognizer-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthe-full-stack%2Ffsdl-text-recognizer-project/lists"}