{"id":13499066,"url":"https://github.com/flyyufelix/DenseNet-Keras","last_synced_at":"2025-03-29T03:32:17.757Z","repository":{"id":159500474,"uuid":"91070142","full_name":"flyyufelix/DenseNet-Keras","owner":"flyyufelix","description":"DenseNet Implementation in Keras with ImageNet Pretrained Models","archived":false,"fork":false,"pushed_at":"2019-10-12T18:53:41.000Z","size":170,"stargazers_count":568,"open_issues_count":15,"forks_count":264,"subscribers_count":29,"default_branch":"master","last_synced_at":"2024-10-31T17:39:08.371Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/flyyufelix.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2017-05-12T08:39:09.000Z","updated_at":"2024-10-15T12:35:29.000Z","dependencies_parsed_at":"2023-05-10T12:53:49.449Z","dependency_job_id":null,"html_url":"https://github.com/flyyufelix/DenseNet-Keras","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/flyyufelix%2FDenseNet-Keras","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flyyufelix%2FDenseNet-Keras/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flyyufelix%2FDenseNet-Keras/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flyyufelix%2FDenseNet-Keras/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/flyyufelix","download_url":"https://codeload.github.com/flyyufelix/DenseNet-Keras/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246135766,"owners_count":20729056,"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":"2024-07-31T22:00:27.915Z","updated_at":"2025-03-29T03:32:17.492Z","avatar_url":"https://github.com/flyyufelix.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes"],"sub_categories":["DenseNet"],"readme":"# DenseNet-Keras with ImageNet Pretrained Models\n\nThis is an [Keras](https://keras.io/) implementation of DenseNet with [ImageNet](http://www.image-net.org/) pretrained weights. The weights are converted from [Caffe Models](https://github.com/shicai/DenseNet-Caffe). The implementation supports both [Theano](http://deeplearning.net/software/theano/) and [TensorFlow](https://www.tensorflow.org/) backends.\n\nTo know more about how DenseNet works, please refer to the [original paper](https://arxiv.org/abs/1608.06993)\n\n```\nDensely Connected Convolutional Networks\nGao Huang, Zhuang Liu, Kilian Q. Weinberger, Laurens van der Maaten\narXiv:1608.06993\n```\n\n## Pretrained DenseNet Models on ImageNet\n\nThe top-1/5 accuracy rates by using single center crop (crop size: 224x224, image size: 256xN)\n\nNetwork|Top-1|Top-5|Theano|Tensorflow\n:---:|:---:|:---:|:---:|:---:\nDenseNet 121 (k=32)| 74.91| 92.19| [model (32  MB)](https://drive.google.com/open?id=0Byy2AcGyEVxfMlRYb3YzV210VzQ)| [model (32 MB)](https://drive.google.com/open?id=0Byy2AcGyEVxfSTA4SHJVOHNuTXc)\nDenseNet 169 (k=32)| 76.09| 93.14| [model (56  MB)](https://drive.google.com/open?id=0Byy2AcGyEVxfN0d3T1F1MXg0NlU)| [model (56 MB)](https://drive.google.com/open?id=0Byy2AcGyEVxfSEc5UC1ROUFJdmM)\nDenseNet 161 (k=48)| 77.64| 93.79| [model (112 MB)](https://drive.google.com/open?id=0Byy2AcGyEVxfVnlCMlBGTDR3RGs)| [model (112 MB)](https://drive.google.com/open?id=0Byy2AcGyEVxfUDZwVjU2cFNidTA)\n\n## Usage\n\nFirst, download the above pretrained weights to the `imagenet_models` folder.\n\nRun `test_inference.py` for an example of how to use the pretrained model to make inference.\n\n```\npython test_inference.py\n```\n\n## Fine-tuning\n\nCheck [this](https://github.com/flyyufelix/cnn_finetune) out to see example of fine-tuning DenseNet with your own dataset.\n\n## Requirements\n\n* Keras ~~1.2.2~~ 2.0.5\n* Theano 0.8.2 or TensorFlow ~~0.12.0~~ 1.2.1\n\n## Updates\n\n* Keras 2.0.5 and TensorFlow 1.2.1 are supported\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflyyufelix%2FDenseNet-Keras","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fflyyufelix%2FDenseNet-Keras","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflyyufelix%2FDenseNet-Keras/lists"}