{"id":13698475,"url":"https://github.com/1044197988/TF.Keras-Commonly-used-models","last_synced_at":"2025-05-04T03:31:25.469Z","repository":{"id":99947734,"uuid":"175417554","full_name":"1044197988/TF.Keras-Commonly-used-models","owner":"1044197988","description":"基于Tensorflow的常用模型，包括分类分割、新型激活、卷积模块，可在Tensorflow2.X下运行。","archived":false,"fork":false,"pushed_at":"2020-06-27T05:28:02.000Z","size":136,"stargazers_count":178,"open_issues_count":1,"forks_count":78,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-11-13T03:34:43.594Z","etag":null,"topics":["dice-loss","image-classification","image-segmentation","jaccard-loss","keras","segmentation-loss","tensorflow","tensorflow2","unet"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/1044197988.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}},"created_at":"2019-03-13T12:35:02.000Z","updated_at":"2024-10-16T13:18:07.000Z","dependencies_parsed_at":"2023-05-11T18:45:57.615Z","dependency_job_id":null,"html_url":"https://github.com/1044197988/TF.Keras-Commonly-used-models","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/1044197988%2FTF.Keras-Commonly-used-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/1044197988%2FTF.Keras-Commonly-used-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/1044197988%2FTF.Keras-Commonly-used-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/1044197988%2FTF.Keras-Commonly-used-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/1044197988","download_url":"https://codeload.github.com/1044197988/TF.Keras-Commonly-used-models/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252283595,"owners_count":21723505,"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":["dice-loss","image-classification","image-segmentation","jaccard-loss","keras","segmentation-loss","tensorflow","tensorflow2","unet"],"created_at":"2024-08-02T19:00:47.480Z","updated_at":"2025-05-04T03:31:24.800Z","avatar_url":"https://github.com/1044197988.png","language":"Python","funding_links":[],"categories":["Model 💛💛💛💛💛\u003ca name=\"Model\" /\u003e"],"sub_categories":["Classification 分类"],"readme":"# TF.Keras-常用型号\n\n__自己整理的一些tensorflow下ķeras实现的模型,可在Tensorflow2.X下运行__\n\n## 提示：以下模型均不包含预训练权重的载入，只是模型的实现；不同的卷积模块大部分在分类分割模型中已包含。\n\n## 分类模型：\n* AlexNet\n* Darknet53\n* DenseNet\n* Dual_path_network\n* GoogleNet\n* MNasNet\n* Resnet34\n* Resnet50\n* SEResNeXt\n* VGG16\n* Squeeze_Excite-Network\n* MobileNetV3\n* Efficientnet\n* SE_HRNet\n* ResNest\n\n## 分割模型：\n* FCN8S\n* ICNet\n* MiniNetv2\n* PSPNet-ResNet50\n* RAUNet-3D\n* Refinenet\n* Segnet\n* Unet\n* Unet_Xception_Resnetblock\n* ResNextFPN\n* Deeplabv2\n* Deeplabv3+\n* FastFCN\n* HRNet\n* ResUNet-a\n* RCNN-UNet\n* Attention Unet\n* RCNN-Attention Unet\n* UNet ++\n### Unet_family:\n#### 不同种类的Unet模型图像分割的实现\n1、UNet -U-Net：用于生物医学图像分割的卷积网络 https://arxiv.org/abs/1505.04597 \u003cbr\u003e\n2、RCNN-UNet-基于U-Net的递归残积卷积神经网络（R2U-Net）用于医学图像分割 https://arxiv.org/abs/1802.06955 \u003cbr\u003e\n3、Attention Unet -Attention U-Net：学习在哪里寻找胰腺 https://arxiv.org/abs/1804.03999 \u003cbr\u003e\n4、RCNN-Attention Unet -Attention R2U-Net：只需将两个最新的高级作品集成在一起（R2U-Net + Attention U-Net） \u003cbr\u003e\n5、嵌套的UNet -UNet ++：用于医学图像分割的嵌套U-Net体系结构 https://arxiv.org/abs/1807.10165 \u003cbr\u003e\n#### 参考:\n[Unet-Segmentation-Pytorch-Nest-of-Unets](https://github.com/bigmb/Unet-Segmentation-Pytorch-Nest-of-Unets) \u003cbr\u003e\n不同点:我的实现初始滤波数32，原始为64。\n\n### 分割损失函数：\n* Focal_Tversky_loss\n* C_Focal_loss\n* B_Focal_loss\n* LovaszSoftmax\n* WeightedCCE\n* jaccard_loss\n* bce_jaccard_loss\n* cce_jaccard_loss\n* dice_loss\n* bce_dice_loss\n* cce_dice_loss\n\n### 分割指标：\n* iou_score\n* jaccard_score\n* f1_score\n* f2_score\n* dice_score\n\n### 新型激活函数：\n* gelu\n* swish\n* mish\n\n### 卷积模块：\n* SE\n* Res2Net\n* Deformable_Conv\n\n### Layer：\n* FRN\n* attention（PAM空间注意力和CAM通道注意力）\n* BiFPN\n\n### Others：\n* TCN（时间卷积网络——解决LSTM的并发问题）\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F1044197988%2FTF.Keras-Commonly-used-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F1044197988%2FTF.Keras-Commonly-used-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F1044197988%2FTF.Keras-Commonly-used-models/lists"}