{ "info": { "author": "Joseph Robinson", "author_email": "robinson.jo@husky.neu.edu", "bugtrack_url": null, "classifiers": [], "description": "Copyright (c) 2017 Joseph Robinson\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.\n\nDescription: # FIW API\n Families In the WIld: A Kinship Recogntion Toolbox. Visit FIW project page to download and learn more! \n \n [https://web.northeastern.edu/smilelab/fiw/](https://web.northeastern.edu/smilelab/fiw/)\n \n **Version 1.0**\n \n This document is incomplete, i.e., work in progress, as is the API itself.\n \n [![N|Solid](reports/teaser_image.jpg)](reports/teaser_image.jpg)\n ------------\n ## Overview\n This API serves as the main code-base for kinship effort with FIW database. In addition, below is detailed description of database (i.e., data and label) structure.\n \n ## Families In the Wild (FIW) Data and Labels\n This documentation describes FIW DB and (working) development kit. This is work in prgress (i.e., still to come are FIW-CNN models, updated benchmarks, more in README (this), and more).\n \n Check out FIW [project page](https://web.northeastern.edu/smilelab/fiw/index.html)\n \n ### Download\n Download [here](https://web.northeastern.edu/smilelab/fiw/download.html)\n \n ### Details of the data\n See pulications below. A more complete list of references can be found [here](https://web.northeastern.edu/smilelab/fiw/publications.html)\n \n ## Reference\n \n ```\n @article{robinson2018fiw,\n title={},\n author={},\n journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},\n year={2018},\n publisher={IEEE}\n }\n \n @InProceedings{kinFG2017,\n author = \"Wang, Shuyang and Robinson, Joseph P and Fu, Yun\",\n title = \"Kinship Verification on Families In The Wild with Marginalized Denoising Metric Learning\",\n booktitle = \"Automatic Face and Gesture Recognition (FG), 2017 12th IEEE International Conference and Workshops on\",\n year = \"2017\",\n }\n \n @InProceedings{robinson2016families,\n author = \"Robinson, Joseph P. and Shao, Ming and Wu, Yue and Fu, Yun\",\n title = \"Families In the Wild (FIW): Large-Scale Kinship Image Database and Benchmarks\",\n booktitle = \"Proceedings of the 2016 ACM on Multimedia Conference\",\n pages = \"242--246\",\n publisher = \"ACM\",\n year = \"2016\"\n }\n \n ```\n \n ######\n ## DB Contents and Structure\n ######\n * FIW_PIDs.csv:    Photo lookup table. Each row is an image instance, containing the following fields:\n * PID:    Photo ID\n * Name:    Surname.firstName (root reference for given family)\n * URL:    Photo URL on web\n * Metadata:   Text caption for photo\n \n * FIW_FIDs.csv:    FID (family)/ Surname lookup table.\n * FID:    Unique ID key assigned to each family.\n * Surname:    Family Name corresponding to FID key.\n \n * FIW_RIDs.csv:   Relationship lookup table with keys [1-9] assigned to relationship types.\n \n * FIDs/\n * FID####/    Contains labels and cropped facial images for members of family (1-1000)\n * MID#/    Face images of family member with ID key , i.e., MID #.\n \n * F####.csv:    File containing member information of each family:\n * relationships  matrix representing relationship\n * names    First name of family member.\n * gender    ender of family member\n \n \n For example:\n ```\n FID0001.csv\n \n \t0 1 2 3 Name Gender\n \t1 0 4 5 name1 female\n \t2 1 0 1 name2 female\n \t3 5 4 0 name3 male\n \t\n ```\n Here we have 3 family members, as seen by the MIDs across columns and down rows.\n \n \n We can see that MID1 is related to MID2 by 4->1 (Parent->Sibling), which of course can be viewed as the inverse, i.e., MID2->MID1 is 1->4. It can also be seen that MID1 and MID3 are Spouses of one another, i.e., 5->5. And so on, and so forth.\n \n \n \n ------------\n ## Project Organization\n \n \n \u251c\u2500\u2500 LICENSE\n \u251c\u2500\u2500 README.md <- The top-level README for developers using this project.\n \u251c\u2500\u2500 data\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 external <- Data from third party sources.\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 interim <- Intermediate data that has been transformed.\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 processed <- The final, canonical data sets for modeling.\n \u2502\u00a0\u00a0 \u2514\u2500\u2500 raw <- The original, immutable data dump.\n \u2502\n \u251c\u2500\u2500 docs <- A default Sphinx project; see sphinx-doc.org for details\n \u2502\n \u251c\u2500\u2500 models <- Trained and serialized models, model predictions, or model summaries\n \u2502\n \u251c\u2500\u2500 notebooks <- Jupyter notebooks.\n \u2502\n \u251c\u2500\u2500 references <- Data dictionaries, manuals, and all other explanatory materials.\n \u2502\n \u251c\u2500\u2500 reports <- Generated analysis as HTML, PDF, LaTeX, etc.\n \u2502\u00a0\u00a0 \u2514\u2500\u2500 figures <- Generated graphics and figures to be used in reporting\n \u2502\n \u251c\u2500\u2500 requirements.txt <- The requirements file for reproducing the analysis environment, e.g.\n \u2502 generated with `pip freeze > requirements.txt`\n \u2502\n \u251c\u2500\u2500 src <- Source code for use in this project.\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 __init__.py <- Makes src a Python module\n \u2502 \u2502\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 data <- Scripts to download or generate data\n \u2502\u00a0\u00a0 \u2502\u00a0\u00a0 \u2514\u2500\u2500 make_dataset.py\n \u2502 \u2502\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 features <- Scripts to turn raw data into features for modeling\n \u2502\u00a0\u00a0 \u2502\u00a0\u00a0 \u2514\u2500\u2500 build_features.py\n \u2502 \u2502\n \u2502\u00a0\u00a0 \u251c\u2500\u2500 models <- Scripts to train models and then use trained models to make\n \u2502 \u2502 \u2502 predictions\n \u2502\u00a0\u00a0 \u2502\u00a0\u00a0 \u251c\u2500\u2500 predict_model.py\n \u2502\u00a0\u00a0 \u2502\u00a0\u00a0 \u2514\u2500\u2500 train_model.py\n \u2502 \u2502\n \u2502\u00a0\u00a0 \u2514\u2500\u2500 visualization <- Scripts to create exploratory and results oriented visualizations\n \u2502\u00a0\u00a0 \u2514\u2500\u2500 visualize.py\n \u2502\n \u2514\u2500\u2500 <- TBD\n \n \n --------\n \n ------------\n ## Installation\n \n \n ## Todos\n ### General\n - [ ] Feature Extraction Module \n - [ ] Metric Learning Module\n - [ ] Fine-tune module\n - [ ] Eval module\n - [ ] End-to-end scripts demoing usage of modules\n \n ### Experiments (TO DO)\n - [ ] VGG Center-Face\n - [ ] ResNet with Metric Learning\n - [ ] ResNet Triplet-loss?\n - [ ] Cross Dataset Eval\n - [ ] Features from different layers of VGG\n \n \n ### License\n \n By downloading the image data you agree to the following terms:\n 1. You will use the data only for non-commercial research and educational purposes.\n 1. You will NOT distribute the above images.\n 1. Northeastern University makes no representations or warranties regarding the data, including but not limited to warranties of non-infringement or fitness for a particular purpose.\n 1.You accept full responsibility for your use of the data and shall defend and indemnify Northeastern University, including its employees, officers and agents, against any and all claims arising from your use of the data, including but not limited to your use of any copies of copyrighted images that you may create from the data.\n \n \n \n ## Authors\n * **Joseph Robinson** - [Github](https://github.com/huskyjo) - [web](http://www.jrobsvision.com)\n \n ######\n ### Contact\n ######\n Please contact Joseph Robinson (robinson.jo@husky.neu.edu) for questions, comments, or bug reports.\n \n \nPlatform: UNKNOWN\nClassifier: Programming Language :: Python :: 3\nClassifier: License :: OSI Approved :: MIT License\nClassifier: Operating System :: OS Independent\n", "description_content_type": "", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/visionjo/FIW_KRT", "keywords": "", "license": "MIT License", "maintainer": "", "maintainer_email": "", "name": "fiwtools", "package_url": "https://pypi.org/project/fiwtools/", "platform": "", "project_url": "https://pypi.org/project/fiwtools/", "project_urls": { "Homepage": "https://github.com/visionjo/FIW_KRT" }, "release_url": "https://pypi.org/project/fiwtools/0.1.0/", "requires_dist": null, "requires_python": "", "summary": "Families In the WIld: A Kinship Recogntion Toolbox.", "version": "0.1.0" }, "last_serial": 4533514, "releases": { "0.1.0": [ { "comment_text": "", "digests": { "md5": "62eef59bf0a8431bb17a69346a38768d", "sha256": "e8268b18ab36e8b43833eb481e66d99e525dbe1a4d00948cecf0a8d8db638847" }, "downloads": -1, "filename": "fiwtools-0.1.0-py3-none-any.whl", "has_sig": false, "md5_digest": "62eef59bf0a8431bb17a69346a38768d", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 6983, "upload_time": "2018-11-27T09:55:36", "url": "https://files.pythonhosted.org/packages/ae/54/914582bd8799d645d8af6947d1c6f23428cafd0a0a3188ef0c58a4478ef0/fiwtools-0.1.0-py3-none-any.whl" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "62eef59bf0a8431bb17a69346a38768d", "sha256": "e8268b18ab36e8b43833eb481e66d99e525dbe1a4d00948cecf0a8d8db638847" }, "downloads": -1, "filename": "fiwtools-0.1.0-py3-none-any.whl", "has_sig": false, "md5_digest": "62eef59bf0a8431bb17a69346a38768d", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 6983, "upload_time": "2018-11-27T09:55:36", "url": "https://files.pythonhosted.org/packages/ae/54/914582bd8799d645d8af6947d1c6f23428cafd0a0a3188ef0c58a4478ef0/fiwtools-0.1.0-py3-none-any.whl" } ] }