{"id":16686706,"url":"https://github.com/mayuanyang/doggy","last_synced_at":"2026-04-13T17:06:13.591Z","repository":{"id":78680684,"uuid":"111197359","full_name":"mayuanyang/doggy","owner":"mayuanyang","description":"An AI model to classify dog's actions","archived":false,"fork":false,"pushed_at":"2017-12-20T23:19:34.000Z","size":87894,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-20T11:25:58.303Z","etag":null,"topics":["keras","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"JavaScript","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/mayuanyang.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":"2017-11-18T10:45:48.000Z","updated_at":"2017-12-21T01:28:42.000Z","dependencies_parsed_at":"2023-05-16T04:01:35.007Z","dependency_job_id":null,"html_url":"https://github.com/mayuanyang/doggy","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/mayuanyang%2Fdoggy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mayuanyang%2Fdoggy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mayuanyang%2Fdoggy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mayuanyang%2Fdoggy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mayuanyang","download_url":"https://codeload.github.com/mayuanyang/doggy/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243437966,"owners_count":20290864,"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":["keras","tensorflow"],"created_at":"2024-10-12T15:06:39.426Z","updated_at":"2025-12-26T17:41:27.895Z","avatar_url":"https://github.com/mayuanyang.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# doggy\nAn AI model to classify dog's actions, it uses Keras and Tensorflow to train and Keras-JS with vuejs as the frontend\n\n## Setup\nFollow this guide to setup the trainning and evaluation environment\n### Amazon DLAMI\nIf you are using Amazon DLAMI, all the AI frameworks should be already installed, follow the start up screen to activate the training environment\n\n### Your Own Environment\nIf you are using your own environment (the recommend way is virtualenv), follow this guide to setup Tensorflow https://www.linode.com/docs/applications/remote-desktop/install-vnc-on-ubuntu-16-04\n\n### Libraries\nWe use Keras in this project, follow this guide to install it https://keras.io/#installation\n\nWe also use `pillow`, run the following command to install it\n```\npip install pillow\n```\n## How to train\n### Clone the repo\nClone this repo and download the images file\n\n### Activate the environment\nActivate the TensorFlow, depends on the environment you are in, e.g. for your local own environment, run this command `source ~/tensorflow/bin/activate`, for DLAMI, run the command for TensorFlow on the welcome screen, usually `source activate tensorflow_p36`\n\n### Start trainning\nDepends on where the images are saved, you might need to change the paths a bit inside `train.py`, change the following as required, by default the `dog_dataset` folder is the same as the `train.py`\n```\n# data dir\ntrain_data_dir = 'dog_dataset/train'\nvalidation_data_dir = 'dog_dataset/test'\n```\nOnce the repo and images are downloaded, run this command in the TensorFlow environment `python train.py`\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmayuanyang%2Fdoggy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmayuanyang%2Fdoggy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmayuanyang%2Fdoggy/lists"}