{"id":13870002,"url":"https://github.com/albertomontesg/keras-model-zoo","last_synced_at":"2025-12-30T18:25:26.667Z","repository":{"id":73036275,"uuid":"55420528","full_name":"albertomontesg/keras-model-zoo","owner":"albertomontesg","description":"Keras Model Zoo","archived":false,"fork":false,"pushed_at":"2016-06-11T09:06:22.000Z","size":3710,"stargazers_count":208,"open_issues_count":7,"forks_count":28,"subscribers_count":15,"default_branch":"master","last_synced_at":"2024-08-06T21:22:55.894Z","etag":null,"topics":["deep-learning","keras","model-zoo"],"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/albertomontesg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":".github/CONTRIBUTING.md","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}},"created_at":"2016-04-04T15:00:55.000Z","updated_at":"2024-06-22T13:33:59.000Z","dependencies_parsed_at":null,"dependency_job_id":"b35bf688-884a-429f-adc9-08b27517c33d","html_url":"https://github.com/albertomontesg/keras-model-zoo","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albertomontesg%2Fkeras-model-zoo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albertomontesg%2Fkeras-model-zoo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albertomontesg%2Fkeras-model-zoo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/albertomontesg%2Fkeras-model-zoo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/albertomontesg","download_url":"https://codeload.github.com/albertomontesg/keras-model-zoo/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226068142,"owners_count":17568703,"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":["deep-learning","keras","model-zoo"],"created_at":"2024-08-05T20:01:24.908Z","updated_at":"2025-12-30T18:25:26.654Z","avatar_url":"https://github.com/albertomontesg.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Keras Model Zoo\nRepository to share all the models that the community has found and worked with the [Keras](https://github.com/fchollet/keras) framework. Official documentation [here](http://keras.io)\n\n## Install\n\nTo install this package you should first download this repository and then proceed with the installation:\n```bash\ngit clone https://github.com/albertomontesg/keras-model-zoo.git\ncd keras-model-zoo\npython setup.py install\n```\nAlso as a pyp package:\n```bash\npip install kerasmodelzoo\n```\n\n## Usage\n\nThe usage is really easy. For each topology available you can load the model and also the mean which was trained with.\n\n```python\nfrom kerasmodelzoo.models.vgg import vgg16\n\nmodel = vgg16.model()\nmean = vgg16.mean\n```\n\nIt is also possible to load the weights or print the summary of the model if you give the parameters set to True:\n\n```python\nfrom kerasmodelzoo.models.vgg import vgg16\n\nmodel = vgg16.model(weights=True, summary=True)\nmean = vgg16.mean\nmodel.compile(loss='mse', optimizer='sgd')\nX = X - mean\nmodel.fit(X, Y)\n```\n\n## Models Available\n\nAt this moment the models available are:\n\n### VGG\n\n\n**Reference**:\n```bibtex\n@article{DBLP:journals/corr/SimonyanZ14a,\n  author    = {Karen Simonyan and\n               Andrew Zisserman},\n  title     = {Very Deep Convolutional Networks for Large-Scale Image Recognition},\n  journal   = {CoRR},\n  volume    = {abs/1409.1556},\n  year      = {2014},\n  url       = {http://arxiv.org/abs/1409.1556},\n  timestamp = {Wed, 01 Oct 2014 15:00:05 +0200},\n  biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/SimonyanZ14a},\n  bibsource = {dblp computer science bibliography, http://dblp.org}\n}\n```\n\n**Framework used**: *Caffe*\n\n**License**: *unrestricted use*\n\n**Dataset used to train**: ILSVRC-2014\n\n\n**Description**:\n\nThis is the [Keras](http://keras.io/) model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition. Project [site](http://www.robots.ox.ac.uk/~vgg/research/very_deep/). Gist where the model was obtained [here](https://gist.github.com/baraldilorenzo/07d7802847aaad0a35d3).\n\nIt has been obtained by directly converting the [Caffe model](https://gist.github.com/ksimonyan/211839e770f7b538e2d8#file-readme-md) provived by the authors.\n\nIn the paper, the VGG-16 model is denoted as configuration `D`. It achieves 7.5% top-5 error on ILSVRC-2012-val, 7.4% top-5 error on ILSVRC-2012-test.\n\nPlease cite the paper if you use the models.\n\n\n### C3D\n\n\n**Reference**:\n\nTran, Du, et al. *\"[Learning Spatiotemporal Features With 3D Convolutional Networks](http://www.cv-foundation.org/openaccess/content_iccv_2015/html/Tran_Learning_Spatiotemporal_Features_ICCV_2015_paper.html).\"* Proceedings of the IEEE International Conference on Computer Vision. 2015.\n\n\n**Framework used**: *[C3D](https://github.com/facebook/C3D) (Caffe fork)*\n\n**Dataset used to train**: [Sports1M](https://github.com/gtoderici/sports-1m-dataset)\n\n\n**Description**:\n\nThis model was trained using a modified [version](https://github.com/facebook/C3D)\nof BVLC Caffe to support 3-Dimensional Convolutional Networks.\nThe C3D pre-trained model provided was trained on Sports-1M dataset and can be\nused to extract 3D-conv features.\n\nHere are some results from the paper using the C3D features.\n\n| Dataset          | UCF101 | ASLAN       | UMD-Scene | YUPENN-Scene | Object |\n| ---------------- | :----: | :---------: | :-------: | :----------: | :----: |\n| C3D + linear SVM | 82.3   | 78.3 (86.5) | 87.7      | 98.1         | 22.3   |\n\nIf used this model, please refer to the citations on the project [website](http://vlg.cs.dartmouth.edu/c3d/).\n\n## Contribute\n\nOn `.github/CONTRIBUTION.md` there is a detailed explanation about how to contribute to this repository with new models.\nEveryone is welcome and invited to participate.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falbertomontesg%2Fkeras-model-zoo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falbertomontesg%2Fkeras-model-zoo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falbertomontesg%2Fkeras-model-zoo/lists"}