{"id":19412709,"url":"https://github.com/tensorlayer/tlxcv","last_synced_at":"2025-04-24T11:31:26.494Z","repository":{"id":93136325,"uuid":"598531817","full_name":"tensorlayer/TLXCV","owner":"tensorlayer","description":"A Platform-agnostic Computer Vision Application Library","archived":false,"fork":false,"pushed_at":"2024-11-06T03:28:28.000Z","size":1423,"stargazers_count":10,"open_issues_count":1,"forks_count":1,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-11-06T04:18:28.495Z","etag":null,"topics":["computer-vision","mindspore","paddlepaddle","pytorch","tensorflow","tensorlayer","tensorlayerx"],"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/tensorlayer.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-02-07T09:58:24.000Z","updated_at":"2024-11-06T03:28:31.000Z","dependencies_parsed_at":"2024-03-18T05:29:33.102Z","dependency_job_id":"e4812705-e341-4d0f-a877-19bde445da37","html_url":"https://github.com/tensorlayer/TLXCV","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/tensorlayer%2FTLXCV","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorlayer%2FTLXCV/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorlayer%2FTLXCV/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorlayer%2FTLXCV/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tensorlayer","download_url":"https://codeload.github.com/tensorlayer/TLXCV/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223951893,"owners_count":17230782,"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":["computer-vision","mindspore","paddlepaddle","pytorch","tensorflow","tensorlayer","tensorlayerx"],"created_at":"2024-11-10T12:27:56.227Z","updated_at":"2024-11-10T12:27:56.905Z","avatar_url":"https://github.com/tensorlayer.png","language":"Python","readme":"# TLXCV\nA Platform-agnostic Computer Vision Application Library, based on [TensorLayerX](https://github.com/tensorlayer/TensorLayerX). \n\n## Introduction\nTLXCV  provides a set of algorithms and high-level APIs for computer vision tasks, such as image classification, object detection, semantic segmentation, etc.   \nSome of the algorithms are converted from [PaddlePaddle](https://github.com/PaddlePaddle) implementations, and some are implemented from scratch.  \n\n## Quick Start\n### Installation\n```bash\ngit clone https://github.com/tensorlayer/TLXCV.git\ncd TLXCV\npip install -e .\n```\n\n### train\n```bash\npython demo/image_classification/train.py\n```\n\n### predict\n```bash\npython demo/image_classification/predict.py\n```\n\n## 模型列表 Models\n### 分类模型 Classification\n\n| 序号 | 模型 | 类别误差 | 前后误差 | 状态 | 参考 |\n| -- | -- | -- | -- | -- | -- |\n| 1 | vgg16(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 2 | alexnet(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 3 | resnet50(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 4 | resnet101(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 5 | googlenet(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 6 | mobilenetv1(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 7 | mobilenetv2(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 8 | mobilenetv3(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 9 | shufflenetv2(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 10 | squeezenet(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 11 | inceptionv3(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 12 | regnet(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 13 | tnt(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 14 | darknet53(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 15 | densenet(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 16 | rednet50(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 17 | rednet101(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 18 | cspdarknet53(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 19 | efficientnet_b1(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 20 | efficientnet_b7(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 21 | dla34(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 22 | dla102(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 23 | dpn68(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 24 | dpn107(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 25 | ghostnet(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 26 | hardnet39(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 27 | hardnet85(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 28 | resnest50(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 29 | resnext50(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 30 | resnext101(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 31 | rexnet(pretrained model) | 微小误差 | 0.00061244145 | 完成 | PaddleClas |\n| 32 | se_resnext(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 33 | esnet_x0_5(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 34 | esnet_x1_0(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 35 | vit(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 36 | alt_gvt_small(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 37 | alt_gvt_base(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 38 | swin_transformer_base(pretrained model) | 0.0 |  |  | PaddleClas |\n| 39 | swin_transformer_small(pretrained model) | 0.0 |  |  | PaddleClas |\n| 40 | pcpvt_base(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 41 | pcpvt_large(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 42 | xception41(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 43 | xception65(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 44 | xception41_deeplab(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 45 | xception65_deeplab(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 46 | levit(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 47 | mixnet(pretrained model) | 微小误差 | 0.00048300158 | 完成 | PaddleClas |\n| 48 | convnext(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 49 | cswin(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 50 | deittiny(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 51 | deitsmall(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 52 | deitbase(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 53 | dvt(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 54 | peleenet(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 55 | pp_hgnet(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 56 | pp_lcnet(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 57 | pp_lcnet_v2(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 58 | pvt_v2(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 59 | res2net(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n| 60 | van(pretrained model) | 一致 | 0.0 | 完成 | PaddleClas |\n\n\n### 分割模型 Segmentation\n\n| 序号 | 模型 | 前后误差 | 状态 | 参考 |\n| -- | -- | -- | -- | -- |\n| 1 | fast_scnn | 0.0 | 完成 | PaddleSeg |\n| 2 | hrnet | 0.0 | 完成 | PaddleSeg |\n| 3 | encnet | 0.0 | 完成 | PaddleSeg |\n| 4 | bisenet | 0.0 | 完成 | PaddleSeg |\n| 5 | fastfcn | 0.0 | 完成 | PaddleSeg |\n| 6 | enet | 0.0 | 完成 | PaddleSeg |\n\n\n### 检测模型 Detection\n\n| 序号 | 模型 | 前后误差 | 状态 | 方向 |\n| -- | -- | -- | -- | -- |\n| 1 | yolov3 | 0.0 | 完成 | PaddleDec |\n| 2 | ssd | 0.0 | 完成 | PaddleDec |\n| 3 | yolox | 0.0 | 完成 | PaddleDec |\n| 4 | picodet_lcnet | 0.0 | 完成 | PaddleDec |\n| 5 | fcos_r50 | 0.0 | 完成 | PaddleDec |\n| 6 | fcos_dcn | 0.0 | 完成 | PaddleDec |\n| 7 | RetinaNet | 0.0 | 完成 | PaddleDec |\n| 8 | Mask_RCNN | 0.0 | 完成 | PaddleDec |\n| 9 | Faster_RCNN | 0.0 | 完成 | PaddleDec |\n| 10 | CascadeRCNN | 0.0 | 完成 | PaddleDec |\n| 11 | SOLOv2 | 0.0 | 完成 | PaddleDec |\n| 12 | GFL | 0.0 | 完成 | PaddleDec |\n| 13 | TOOD | 0.0 | 完成 | PaddleDec |\n| 14 | CenterNet | 0.0 | 完成 | PaddleDec |\n| 15 | TTFNet | 0.0 | 完成 | PaddleDec |\n\n\n### 遥感模型 Remote Sensing\n\n| 序号 | 模型 | 前后误差 | 状态 | 参考 | \n| -- | -- | -- | -- | -- |\n| 1 | bit | 0.0 | 完成 | PaddleRS |\n| 2 | cdnet | 0.0 | 完成 | PaddleRS |\n| 3 | stanet | 0.0 | 完成 | PaddleRS |\n| 4 | fcef | 0.0 | 完成 | PaddleRS |\n| 5 | fccdn | 0.0 | 完成 | PaddleRS |\n| 6 | dsamnet | 0.0 | 完成 | PaddleRS |\n| 7 | snunet | 0.0 | 完成 | PaddleRS |\n| 8 | dsifn | 0.0 | 完成 | PaddleRS |\n| 9 | unet | 0.0 | 完成 | PaddleRS |\n| 10 | farseg | 0.0 | 完成 | PaddleRS |\n| 11 | deeplab | 0.0 | 完成 | PaddleRS |\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftensorlayer%2Ftlxcv","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftensorlayer%2Ftlxcv","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftensorlayer%2Ftlxcv/lists"}