{"id":18927601,"url":"https://github.com/gentaiscool/cnn-autoencoder-tf","last_synced_at":"2026-03-17T02:37:22.442Z","repository":{"id":74030775,"uuid":"135675162","full_name":"gentaiscool/cnn-autoencoder-tf","owner":"gentaiscool","description":"CNN and Contrastive Autoencoder (CAE) on EMNIST using Tensorflow","archived":false,"fork":false,"pushed_at":"2018-10-07T12:16:02.000Z","size":100649,"stargazers_count":10,"open_issues_count":1,"forks_count":6,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-28T22:11:23.539Z","etag":null,"topics":["autoencoder","cae","cnn","contrastive","emnist","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/gentaiscool.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}},"created_at":"2018-06-01T06:11:43.000Z","updated_at":"2024-09-25T02:19:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"bfb20455-ed5f-4f47-bbd1-b01569d891ee","html_url":"https://github.com/gentaiscool/cnn-autoencoder-tf","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/gentaiscool%2Fcnn-autoencoder-tf","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gentaiscool%2Fcnn-autoencoder-tf/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gentaiscool%2Fcnn-autoencoder-tf/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gentaiscool%2Fcnn-autoencoder-tf/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gentaiscool","download_url":"https://codeload.github.com/gentaiscool/cnn-autoencoder-tf/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249080634,"owners_count":21209553,"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":["autoencoder","cae","cnn","contrastive","emnist","tensorflow"],"created_at":"2024-11-08T11:19:42.828Z","updated_at":"2026-03-17T02:37:17.411Z","avatar_url":"https://github.com/gentaiscool.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Convolutional Neural Network and Contrastive Autoencoder on EMNIST\n\nIn this project, we are going to evaluate the performance of convolutional neural network (CNN) and contrastive autoencoder (CAE) models by conducting empirical study on simple image data (EMNIST dataset) [1]. This dataset consists of 28x28 images of handwritten characters that belong to 47 classes.\n\n[1] Gregory Cohen, Saeed Afshar, Jonathan Tapson, and Andre van Schaik. EMNIST: an\nextension of MNIST to handwritten letters. arXiv preprint arXiv:1702.05373, 2017.\n\n### Run the code\n#### Package required\n- Python 3.5 (or later)\n- Tensorflow (https://www.tensorflow.org/)\n\n#### Parameters\n- lr: initial learning rate\n- mm: momentum\n- bsz: batch size\n\n### CNN\n\n#### Run the code\nTrain CNN\n```\npython --task=\"train_cnn\" --lr=0.1 --mm=0.2 --bsz=32\n```\n\nCross Validation CNN\n```\npython --task=\"cross_valid_cnn\"\n```\n\nTest CNN\n```\npython --task=\"test_cnn\" --lr=0.1 --mm=0.2 --bsz=32\n```\n\n### Autoencoder\n\n\u003cimg src=\"fig/sample.png\" height=350/\u003e\n\n#### Run the code\nTrain AE\n```\npython --task=\"train_ae\" --lr=0.1 --mm=0.2 --bsz=32\n```\n\nCross Validation AE\n```\npython --task=\"cross_valid_ae\"\n```\n\nTest AE\n```\npython --task=\"evaluate_ae\" --lr=0.1 --mm=0.2 --bsz=32\n```\n\n### Note\n\nCOMP5212 - Machine Learning Programming Assignment 2 in HKUST\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgentaiscool%2Fcnn-autoencoder-tf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgentaiscool%2Fcnn-autoencoder-tf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgentaiscool%2Fcnn-autoencoder-tf/lists"}