{"id":20541744,"url":"https://github.com/maluuba/geneva_datasets","last_synced_at":"2025-07-27T06:35:45.915Z","repository":{"id":150071691,"uuid":"185669638","full_name":"Maluuba/GeNeVA_datasets","owner":"Maluuba","description":"Scripts to generate the CoDraw and i-CLEVR datasets used for the GeNeVA task proposed in our ICCV 2019 paper \"Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction\"","archived":false,"fork":false,"pushed_at":"2023-05-16T14:49:52.000Z","size":14,"stargazers_count":39,"open_issues_count":0,"forks_count":9,"subscribers_count":22,"default_branch":"master","last_synced_at":"2025-04-14T09:09:00.187Z","etag":null,"topics":["chatpainter","codraw","computer-vision","gan","generative-adversarial-networks","generative-neural-visual-artist","geneva","geneva-datasets","geneva-gan","i-clevr","iccv","iccv-2019","iccv2019","interactive-image-generation","keep-drawing-it","recurrent-gan","tell-draw-repeat"],"latest_commit_sha":null,"homepage":"https://www.microsoft.com/en-us/research/project/generative-neural-visual-artist-geneva/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Maluuba.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-05-08T19:45:02.000Z","updated_at":"2025-01-15T11:39:23.000Z","dependencies_parsed_at":null,"dependency_job_id":"9774db6a-bb45-4de4-865a-ae949283c969","html_url":"https://github.com/Maluuba/GeNeVA_datasets","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Maluuba/GeNeVA_datasets","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Maluuba%2FGeNeVA_datasets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Maluuba%2FGeNeVA_datasets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Maluuba%2FGeNeVA_datasets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Maluuba%2FGeNeVA_datasets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Maluuba","download_url":"https://codeload.github.com/Maluuba/GeNeVA_datasets/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Maluuba%2FGeNeVA_datasets/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267317713,"owners_count":24068481,"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":"2025-07-27T02:00:11.917Z","response_time":82,"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":["chatpainter","codraw","computer-vision","gan","generative-adversarial-networks","generative-neural-visual-artist","geneva","geneva-datasets","geneva-gan","i-clevr","iccv","iccv-2019","iccv2019","interactive-image-generation","keep-drawing-it","recurrent-gan","tell-draw-repeat"],"created_at":"2024-11-16T01:25:53.646Z","updated_at":"2025-07-27T06:35:45.896Z","avatar_url":"https://github.com/Maluuba.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Generative Neural Visual Artist (GeNeVA) - Datasets - Generation Code\n\nScripts to generate the `CoDraw` and `i-CLEVR` datasets used for the `GeNeVA` task proposed in [Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction](https://arxiv.org/abs/1811.09845).\n\n## Setup ##\n\n### 1. Install Miniconda\n\n    wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh\n    bash Miniconda3-latest-Linux-x86_64.sh\n    rm Miniconda3-latest-Linux-x86_64.sh\n\nYou will now have to restart your shell for the path changes to take effect.\n\n### 2. Clone the repository\n\n    git clone git@github.com:Maluuba/GeNeVA_datasets.git  # use https://github.com/Maluuba/GeNeVA_datasets.git for HTTPS\n    cd GeNeVA_datasets\n\n### 3. Create a conda environment for this repository\n\n    conda env create -f environment.yml\n\n### 4. Activate the environment\n\n    source activate geneva\n\n### 5. Download external data files\n\n    ./scripts/download_data.sh\n\n### 6. Download GeNeVA data files to the repository\n\nDownload the [GeNeVA zip file](https://www.microsoft.com/en-us/research/project/generative-neural-visual-artist-geneva/) and extract it as specified below:\n - `GeNeVA-v1.zip`\n    ```\n    unzip GeNeVA-v1.zip\n    ```\n    Please review the LICENSE for the GeNeVA zip file in the extracted `GeNeVA-v1` folder\n - `data.rar`: pre-generated data files for both datasets\n    ```\n    rar x GeNeVA-v1/data.rar ./  # `sudo apt-get install rar` if rar is not installed\n    ```\n - `CoDraw_images.rar`: CoDraw images for each scene's json\n    ```\n    rar x GeNeVA-v1/CoDraw_images.rar raw-data/CoDraw\n    ```\n - `i-CLEVR.rar`: i-CLEVR scene images, scene jsons, background image\n    ```\n    rar x GeNeVA-v1/i-CLEVR.rar raw-data/\n    ```\n\n### 7. Generate dataset HDF5 files\n\n - Vocabulary\n    ```\n    python scripts/joint_codraw_iclevr/generate_glove_file.py\n    ```\n - CoDraw\n    ```\n    python scripts/codraw_dataset_generation/codraw_add_data_to_raw.py\n    python scripts/codraw_dataset_generation/codraw_raw_to_hdf5.py       # dataset for GeNeVA-GAN\n    python scripts/codraw_dataset_generation/codraw_object_detection.py  # dataset for Object Detector \u0026 Localizer\n    ```\n - i-CLEVR\n    ```\n    python scripts/iclevr_dataset_generation/iclevr_add_data_to_raw.py\n    python scripts/iclevr_dataset_generation/iclevr_raw_to_hdf5.py       # dataset for GeNeVA-GAN\n    python scripts/iclevr_dataset_generation/iclevr_object_detection.py  # dataset for Object Detector \u0026 Localizer\n    ```\n\n### 8. (Optional) Downloaded data can now be deleted\n\n    rm raw-data/ -rf\n    rm GeNeVA-v1/ -rf\n    rm GeNeVA-v1.zip\n\n## Reference ##\nIf you use this code or the GeNeVA datasets as part of any published research, please cite the following paper:\n\nAlaaeldin El-Nouby, Shikhar Sharma, Hannes Schulz, Devon Hjelm, Layla El Asri, Samira Ebrahimi Kahou, Yoshua Bengio, and Graham W. Taylor.\n**\"Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction\"**\n*arXiv preprint arXiv:1811.09845* (2018).\n\n```bibtex\n@article{elnouby2018tell_draw_repeat,\n    author  = {El{-}Nouby, Alaaeldin and Sharma, Shikhar and Schulz, Hannes and Hjelm, Devon and El Asri, Layla and Ebrahimi Kahou, Samira and Bengio, Yoshua and Taylor, Graham W.},\n    title   = {Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction},\n    journal = {CoRR},\n    volume  = {abs/1811.09845},\n    year    = {2018},\n    url     = {http://arxiv.org/abs/1811.09845},\n    archivePrefix = {arXiv},\n    eprint  = {1811.09845}\n}\n```\n\n## Microsoft Open Source Code of Conduct ##\nThis project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).\nFor more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)\nor contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.\n\n## License ##\nSee [LICENSE.txt](LICENSE.txt).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaluuba%2Fgeneva_datasets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmaluuba%2Fgeneva_datasets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaluuba%2Fgeneva_datasets/lists"}