{"id":19623448,"url":"https://github.com/airaria/dogbreedidentification_rosettastone","last_synced_at":"2025-08-01T19:31:58.246Z","repository":{"id":87909961,"uuid":"118094637","full_name":"airaria/DogBreedIdentification_RosettaStone","owner":"airaria","description":"Using tensorflow and pytorch to classify dog breeds ( kaggle competition)","archived":false,"fork":false,"pushed_at":"2018-01-19T08:53:07.000Z","size":195,"stargazers_count":18,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-28T04:34:47.553Z","etag":null,"topics":["classification","dog","kaggle","pytorch","tensorflow"],"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/airaria.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":"2018-01-19T07:51:01.000Z","updated_at":"2024-11-07T13:33:45.000Z","dependencies_parsed_at":null,"dependency_job_id":"f5b5b9ce-1650-4799-ac6a-63f036178d45","html_url":"https://github.com/airaria/DogBreedIdentification_RosettaStone","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/airaria/DogBreedIdentification_RosettaStone","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airaria%2FDogBreedIdentification_RosettaStone","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airaria%2FDogBreedIdentification_RosettaStone/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airaria%2FDogBreedIdentification_RosettaStone/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airaria%2FDogBreedIdentification_RosettaStone/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/airaria","download_url":"https://codeload.github.com/airaria/DogBreedIdentification_RosettaStone/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airaria%2FDogBreedIdentification_RosettaStone/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268285942,"owners_count":24225831,"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","status":"online","status_checked_at":"2025-08-01T02:00:08.611Z","response_time":67,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["classification","dog","kaggle","pytorch","tensorflow"],"created_at":"2024-11-11T11:33:46.735Z","updated_at":"2025-08-01T19:31:58.176Z","avatar_url":"https://github.com/airaria.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Dog Breed Identification\nFine-tune pretrained models in tensorflow and pytorch to identify dog breeds, mostly for pedagogical purpose. \n\n## Purpose of the repo\nis to show how to \n- load and fine-tune pretrained model in tensorflow and pytorch,\n- read large dataset using the **dataset** paradigm in tensorflow and pytorch,\n- do data augmentation on image data in tensorflow and pytorch,\n- make a comparision between tensorflow and pytorch.\n\n## Prerequisites\n\n- tensorflow \u003e= 1.3\n- pytorch \u003e= 0.3\n- numpy, pandas, sklearn, Pillow\n\n## Usage\n1. Download the data from kaggle: www.kaggle.com/c/dog-breed-identification \n\n2. Unzip labels.csv.zip and train.zip and put them under data/ folder,  now the data/ folder contains labels.csv and a new folder train/  .\n\n3. To train pytorch model, run\n\n```shell\npython pytorch_version/main.py\n```\n\n4. To train tensorflow model, download inceptionV3 model file from https://github.com/tensorflow/models/tree/master/research/slim , unzip, and put it under tf_version/, run:\n\n```shell\npython tf_version/main.py\n```\n\n## Results\nAfter 10 training epochs:\n- tensorflow model (using InceptionV3): mean accuracy reaches 90% on val set.\n- pytorch model (using Resnet50): mean accuracy reaches 87% on val set.\n\n## Acknowledgments\n\ntf_version/preprocessing and tf_version/nets are borrowed from slim :https://github.com/tensorflow/models/tree/master/research/slim\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fairaria%2Fdogbreedidentification_rosettastone","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fairaria%2Fdogbreedidentification_rosettastone","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fairaria%2Fdogbreedidentification_rosettastone/lists"}