{"id":20068227,"url":"https://github.com/phtrempe/l2a","last_synced_at":"2026-05-05T01:37:17.016Z","repository":{"id":169851739,"uuid":"103673408","full_name":"PhTrempe/l2a","owner":"PhTrempe","description":"This is a small project which aims to show an example of applied machine learning in Python 3 with the Keras library and its TensorFlow backend to train a neural network model for it to learn to add two integers.","archived":false,"fork":false,"pushed_at":"2017-09-24T20:02:41.000Z","size":10,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-01-12T23:30:22.168Z","etag":null,"topics":["applied","data","data-science","deep-learning","keras","machine-learning","neural-network","tensorboard","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","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/PhTrempe.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}},"created_at":"2017-09-15T15:35:05.000Z","updated_at":"2017-09-24T20:08:30.000Z","dependencies_parsed_at":"2024-08-06T08:04:13.953Z","dependency_job_id":null,"html_url":"https://github.com/PhTrempe/l2a","commit_stats":null,"previous_names":["phtrempe/l2a"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PhTrempe%2Fl2a","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PhTrempe%2Fl2a/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PhTrempe%2Fl2a/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PhTrempe%2Fl2a/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PhTrempe","download_url":"https://codeload.github.com/PhTrempe/l2a/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241495174,"owners_count":19972044,"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":["applied","data","data-science","deep-learning","keras","machine-learning","neural-network","tensorboard","tensorflow"],"created_at":"2024-11-13T14:05:51.575Z","updated_at":"2026-05-05T01:37:11.955Z","avatar_url":"https://github.com/PhTrempe.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# l2a (Learn to Add)\n\n## Description\n\nThis is a small project which aims to show an example of applied machine \nlearning in Python 3 with the Keras library and its TensorFlow backend to \ntrain a neural network model for it to learn to add two integers.\n\nThe project also aims to follow the 7 Steps of Machine Learning presented by \nGoogle in [this](https://www.youtube.com/watch?v=nKW8Ndu7Mjw) YouTube video.\n\n1. Gathering Data (`dataset_generator.py`)\n1. Preparing Data (`dataset_preparer.py`)\n1. Choosing a Model (`model_builder.py`)\n1. Training (`trainer.py`)\n1. Evaluation (`trainer.py`)\n1. Hyperparameter Tuning (`hyperparameters.py`)\n1. Prediction (`predictor.py`)\n\n# Usage\n\n## Installing Dependencies\n\n    conda install numpy scipy\n    pip install tensorflow tensorflow-gpu keras h5py\n\n## Running the Training Process\n\n    python trainer.py\n\nThis will first generate a dataset if none exists yet. \nIt will then prepare the dataset if no prepared dataset exists yet.\nAfter that, it will build the model using the model builder \n(cf. `model_builder.py`) if no model exists yet. \nIf an existing model is found, this model will be loaded to continue its \ntraining.\nOnce the prepared dataset and model are loaded, the training process is started.\nN.B. Feel free to cancel the training process at any point, since it will be\npossible to resume it later on by running the trainer again.\n\n## Visualizing Training with TensorBoard\n\n    tensorboard --logdir=./logs\n\n## Running Predictions\n\nThis will build the model using the model builder \n(cf. `model_builder.py`) if no model exists yet. \nIf an existing model is found, this model will be loaded.\nOnce the model is loaded, it is used to make predictions on given inputs.\n\n    python predictor.py\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphtrempe%2Fl2a","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fphtrempe%2Fl2a","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphtrempe%2Fl2a/lists"}