{"id":16271999,"url":"https://github.com/logcreative/quickdraw-classifier","last_synced_at":"2025-04-08T15:44:51.066Z","repository":{"id":54634866,"uuid":"494460201","full_name":"LogCreative/quickdraw-classifier","owner":"LogCreative","description":"CS420 Project","archived":false,"fork":false,"pushed_at":"2022-06-19T09:05:29.000Z","size":4128,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-14T12:17:36.009Z","etag":null,"topics":[],"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/LogCreative.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}},"created_at":"2022-05-20T12:44:13.000Z","updated_at":"2022-06-19T16:00:35.000Z","dependencies_parsed_at":"2022-08-13T22:10:54.562Z","dependency_job_id":null,"html_url":"https://github.com/LogCreative/quickdraw-classifier","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/LogCreative%2Fquickdraw-classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LogCreative%2Fquickdraw-classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LogCreative%2Fquickdraw-classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LogCreative%2Fquickdraw-classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LogCreative","download_url":"https://codeload.github.com/LogCreative/quickdraw-classifier/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247873994,"owners_count":21010572,"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":[],"created_at":"2024-10-10T18:15:44.544Z","updated_at":"2025-04-08T15:44:51.048Z","avatar_url":"https://github.com/LogCreative.png","language":"Python","readme":"# quickdraw-classifier\nCS420 Project\n\n\n## Data\n\nUnzip the data into `dataset/seq` folder.\n\nUse `RPCL-pix2seq` to covert the seq data into png data. (You may need to clone this repo by `--recursive` parameter to download the submodule.)\n\n```cmd\ncd RPCL-pix2seq\npython seq2png.py --input_dir=../dataset/seq --output_dir=../dataset/png --png_width=28 --categories={'bear'}\n```\n\n\u003e **NOTICE** You need to use python\u003c=3.7 to install tensorflow 1.15.\n\n## Train\n\nOnce the data is prepared, you could train the model by running python on one of the following scripts:\n```\npython train_cnn.py\npython train_rnn.py\npython train_cnnrnn.py\n```\nFor CNN model, you may need to modify the type of the structure in `config_train_cnn.py`. The value of `model` could be `resnet18`, `ResNet`, or `sketchnet`. For RNN model, we use Bidirectional LSTM structure. For CNN-RNN model, we use Sketch-a-Net for CNN branch and BiLSTM for RNN branch.\n\nThe training process uses PyTorch. During training, the best model will be saved as `best_{model}.pth` in the root folder. The test accuracy could be viewed in [report/result.dat](report/result.dat).\n\n## Report\n\nReport (Chinese) could be found in [report/ML_CS420_Project_report.pdf](report/ML_CS420_Project_report.pdf).\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flogcreative%2Fquickdraw-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flogcreative%2Fquickdraw-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flogcreative%2Fquickdraw-classifier/lists"}