{"id":24288638,"url":"https://github.com/ppodds/ncualgorithmtermproject","last_synced_at":"2026-04-12T16:10:33.841Z","repository":{"id":103819323,"uuid":"349810817","full_name":"ppodds/NCUAlgorithmTermProject","owner":"ppodds","description":"NCU Algorithm Term Project (1092)","archived":false,"fork":false,"pushed_at":"2021-05-26T09:54:31.000Z","size":1487,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-16T10:33:15.787Z","etag":null,"topics":["cnn-classification","keras","python","tensorflow2"],"latest_commit_sha":null,"homepage":"","language":"Python","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/ppodds.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-03-20T18:55:25.000Z","updated_at":"2021-09-05T08:17:14.000Z","dependencies_parsed_at":null,"dependency_job_id":"b3e6f3f1-399d-43ef-9c31-581e77c4555c","html_url":"https://github.com/ppodds/NCUAlgorithmTermProject","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ppodds%2FNCUAlgorithmTermProject","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ppodds%2FNCUAlgorithmTermProject/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ppodds%2FNCUAlgorithmTermProject/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ppodds%2FNCUAlgorithmTermProject/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ppodds","download_url":"https://codeload.github.com/ppodds/NCUAlgorithmTermProject/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242123948,"owners_count":20075461,"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":["cnn-classification","keras","python","tensorflow2"],"created_at":"2025-01-16T10:20:13.631Z","updated_at":"2026-04-12T16:10:33.800Z","avatar_url":"https://github.com/ppodds.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NCU Algorithm Term Project (1092)\n[![Python](https://img.shields.io/badge/python-3.8.7-green)](https://www.python.org/doc/versions/)\n[![Colab](https://img.shields.io/badge/Google%20Colab-1.0.2-green)](https://colab.research.google.com/drive/1OspRKKJob_opurnCR-IcOGrCxLRAmp0Z?usp=sharing)\n\nA Chinese number classification AI based on ResNet 9 and ResNet 152.\n\n## Requirements\nThis project is written by Python 3.8.7 . Following packages are need to be installed.\n- tensorflow~=2.4.1\n- pydot\u003e=1.4.2\n- numpy~=1.19.5\n- Pillow~=8.1.2\n\n\n## Installation\n\n```shell script\ngit clone https://github.com/ppodds/NCUAlgorithmTeamProject.git\npython -m pip install -r requirements.txt\n```\n\n## Usage\n\nYou can use Google Colab or run at your own computer. [Link](https://colab.research.google.com/drive/1OspRKKJob_opurnCR-IcOGrCxLRAmp0Z?usp=sharing)\nIf you want to use Colab, you should mount your own google drive (prepare dataset).\n\nIf you want to run this in your own computer, you should check your project structure is correct.\nCheck your dataset path is correct. The path is strictly required to be correct \n\n## Screenshot (Running on Colab)\n\n### ResNet 9 model\n\nBatch size: 64\nEpochs: 35\n![](Documents/ResNet9%20Epoch35.png)\n\n### ResNet 152 model\n\nBatch size: 64\nEpochs: 35\n![](Documents/ResNet152%20Epoch35.png)\n\n## Project Structure\n\n```\nproject\n│   README.md\n│   .gitignore\n│   requirements.txt    \n│\n└───NumberDectect\n    │   main.py\n    │\n    │\n    └───ChineseNumDataset\n    │   │   train_image\n    │   │   validation_image\n    │   │   test_image\n    │\n    └───commands\n    │   │   __init__.py\n    │   │   evaluate.py\n    │   │   info.py\n    │   │   train.py\n    │ \n    └───dataset\n    │   │   __init__.py\n    │\n    └───model\n        │   __init__.py\n        │   ResNet.py\n        │\n        └───layers\n           │   __init__.py\n```\n\n## ResNet Structure\n\n### ResNet 9 model\n\n[source](https://blog.csdn.net/yyyerica/article/details/86541473)\n\n\u003ctable\u003e\n  \u003ctr\u003e\n  \u003cth\u003eLayer Name\u003c/th\u003e\n    \u003cth\u003eOutput size  \u003c/th\u003e\n    \u003cth\u003eDetail\u003c/th\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n  \u003cth\u003eConv1\u003c/th\u003e\n    \u003ctd\u003e28x28x16\u003c/td\u003e\n    \u003ctd\u003e3x3, 16, stride 1\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n  \u003cth\u003eConv2\u003c/th\u003e\n    \u003ctd\u003e14x14x16\u003c/td\u003e\n    \u003ctd\u003e3x3, 16, stride 2 (shortcut)\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n  \u003cth\u003eConv2\u003c/th\u003e\n    \u003ctd\u003e14x14x16\u003c/td\u003e\n    \u003ctd\u003e3x3, 16, stride 1 \u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n  \u003cth\u003eConv3\u003c/th\u003e\n    \u003ctd\u003e7x7x32\u003c/td\u003e\n    \u003ctd\u003e3x3, 16, stride 2 (shortcut)\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n  \u003cth\u003eConv3\u003c/th\u003e\n    \u003ctd\u003e7x7x32\u003c/td\u003e\n    \u003ctd\u003e3x3, 16, stride 1\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n  \u003cth\u003eAvg\u003c/th\u003e\n    \u003ctd\u003e1x1x32\u003c/td\u003e\n    \u003ctd\u003e7x7 average pool\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n  \u003cth\u003eOutput\u003c/th\u003e\n    \u003ctd\u003e10\u003c/td\u003e\n    \u003ctd\u003eflatten, dense, softmax\u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n![](Documents/Res9.png)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fppodds%2Fncualgorithmtermproject","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fppodds%2Fncualgorithmtermproject","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fppodds%2Fncualgorithmtermproject/lists"}