{"id":19011266,"url":"https://github.com/drakmord2/deeplearning-models","last_synced_at":"2026-04-13T21:31:45.662Z","repository":{"id":37224365,"uuid":"262706521","full_name":"Drakmord2/deeplearning-models","owner":"Drakmord2","description":"Implementation of Deeplearning Models","archived":false,"fork":false,"pushed_at":"2022-12-08T09:53:05.000Z","size":50,"stargazers_count":0,"open_issues_count":16,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-21T15:51:30.277Z","etag":null,"topics":["deep-learning","machine-learning","python3","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/Drakmord2.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}},"created_at":"2020-05-10T03:46:05.000Z","updated_at":"2020-09-02T00:02:14.000Z","dependencies_parsed_at":"2023-01-25T06:15:24.883Z","dependency_job_id":null,"html_url":"https://github.com/Drakmord2/deeplearning-models","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Drakmord2/deeplearning-models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Drakmord2%2Fdeeplearning-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Drakmord2%2Fdeeplearning-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Drakmord2%2Fdeeplearning-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Drakmord2%2Fdeeplearning-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Drakmord2","download_url":"https://codeload.github.com/Drakmord2/deeplearning-models/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Drakmord2%2Fdeeplearning-models/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31771813,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T20:17:16.280Z","status":"ssl_error","status_checked_at":"2026-04-13T20:17:08.216Z","response_time":93,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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","machine-learning","python3","tensorflow"],"created_at":"2024-11-08T19:13:55.306Z","updated_at":"2026-04-13T21:31:45.637Z","avatar_url":"https://github.com/Drakmord2.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DeepLearning Models\nThis repository is a collection of [Deep Learning](https://en.wikipedia.org/wiki/Deep_learning) models implemented with knowlegde from\nDeepLearning.ai Specialization on [Coursera](https://www.coursera.org/specializations/deep-learning).\n\n## Algorithms\n### Deep Neural Network\nImplemented using Numpy vectorization. \n\nXavier initialization for network weights.\n\nActivation Functions:\n- Hidden layers : Leaky ReLU\n- Output layer: Sigmoid\n\nIncludes brackpropagation using Gradient Descent or Adam optimization.\nThe latter uses mini-batch.\n\n### TensorFlow Deep Neural Network\nImplemented with TensorFlow 1\n\nXavier initialization for network weights, Adam optimization and mini-batch.\n\nActivation Functions:\n- Hidden layers : Mish\n- Output layer: Softmax\n\n### Keras Convolutional Network\nImplemented with Keras 2\n\nConvolutional Layer:\n- Zero Padding\n- Batch Normalization\n- ReLU Activation\n- Max Pooling\n\nDense layer:\n- Flatten\n- Softmax\n\n### TensorFlow Deep Q Network\nReinforcement Learning heavily based on [lufficc/dqn](https://github.com/lufficc/dqn).\n\nIntended to be used as an agent on OpenAI Gym.\n\n\n## Models\nThe constructor of the models receive:\n- `model ( layers_dimension, num_features, num_classes, learning_rate, num_iterations, beta1, beta2)`\n  - **layers_dimension** is a list with the amount of units in each layer. e.g. \\[784, 800, 300, 10\\] is the dimension of a NN with a 1 input layer, 2 hidden layers and 1 output layer.\n  - **beta1** and **beta2** are Adam parameters\n\nThe main public methods of the models are:\n\n- `fit ( training_inputs, training_labels, optimizer )` - Trains the Neural Network and saves it's parameters in a .npy file\n- `predict ( test_inputs )` - Classify new data\n- `get_accuracy ( test_inputs, test_labels, type )` - Get accuracy of predictions made on a labeled dataset\n\n## Datasets\nThe included utility functions can fetch datasets from OpenML. The default dataset is:\n\n### MNIST \nThe [MNIST database](https://en.wikipedia.org/wiki/MNIST_database) is a large database of handwritten digits that contain 70,000 images. \n\n## Setup\n\nGlobal requirements are Python 3.6+ and [Virtualenv](https://virtualenv.pypa.io/en/latest/). \n\nConfigure the system by executing the following commands on the project's root folder:\n\n```\nvirtualenv venv\nsource venv/bin/activate\npip install -r requirements.txt\n```\n\nWhen inside the virtual environment, the code can be run using `python main.py`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrakmord2%2Fdeeplearning-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdrakmord2%2Fdeeplearning-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrakmord2%2Fdeeplearning-models/lists"}