{"id":18157190,"url":"https://github.com/ffiirree/cv-models","last_synced_at":"2026-03-08T22:33:23.797Z","repository":{"id":64660928,"uuid":"385152249","full_name":"ffiirree/cv-models","owner":"ffiirree","description":"Models for Computer Vision","archived":false,"fork":false,"pushed_at":"2024-12-10T15:52:03.000Z","size":701,"stargazers_count":19,"open_issues_count":2,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-06-03T07:27:19.202Z","etag":null,"topics":["efficientnet","imageclassification","mobilenet","models","pytorch","resnet","shufflenet"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ffiirree.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,"zenodo":null}},"created_at":"2021-07-12T06:52:28.000Z","updated_at":"2025-01-16T21:00:25.000Z","dependencies_parsed_at":"2025-05-06T21:08:27.672Z","dependency_job_id":"8d9ba1a8-5969-4224-a2e0-f427f2785e8d","html_url":"https://github.com/ffiirree/cv-models","commit_stats":null,"previous_names":[],"tags_count":11,"template":false,"template_full_name":null,"purl":"pkg:github/ffiirree/cv-models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ffiirree%2Fcv-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ffiirree%2Fcv-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ffiirree%2Fcv-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ffiirree%2Fcv-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ffiirree","download_url":"https://codeload.github.com/ffiirree/cv-models/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ffiirree%2Fcv-models/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30275569,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-08T20:45:49.896Z","status":"ssl_error","status_checked_at":"2026-03-08T20:45:49.525Z","response_time":56,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["efficientnet","imageclassification","mobilenet","models","pytorch","resnet","shufflenet"],"created_at":"2024-11-02T06:05:37.898Z","updated_at":"2026-03-08T22:33:23.778Z","avatar_url":"https://github.com/ffiirree.png","language":"Python","readme":"# Computer Vision Models\n\n## Backbones\n\n- [x] [`AlexNet`](cvm/models/alexnet.py) - [ImageNet Classification with Deep Convolutional Neural Networks](https://papers.nips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf), NeurIPS, 2012\n- [x] [`VGGNets`](cvm/models/vggnet.py) - [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/abs/1409.1556), 2014\n- [x] [`GoogLeNet`](cvm/models/googlenet.py) - [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842), 2014\n- [x] [`Inception-V3`](cvm/models/inception_v3.py) - [Rethinking the Inception Architecture for Computer Vision](https://arxiv.org/abs/1512.00567), 2015\n- [x] [`Inception-V4 and Inception-ResNet`](cvm/models/inception_v4.py) - [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://arxiv.org/abs/1602.07261), AAAI, 2016\n- [x] [`ResNet`](cvm/models/resnet.py) - [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385), 2015\n- [x] [`SqueezeNet`](cvm/models/squeezenet.py) - [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \u003c0.5MB model size](https://arxiv.org/abs/1602.07360), 2016\n- [x] [`ResNeXt`](cvm/models/resnet.py) - [Aggregated Residual Transformations for Deep Neural Networks](https://arxiv.org/abs/1611.05431), CVPR, 2016\n- [ ] `Res2Net` - [Res2Net: A New Multi-scale Backbone Architecture](https://arxiv.org/abs/1904.01169), TPAMI, 2019\n- [x] [`ReXNet`](cvm/models/rexnet.py) - [Rethinking Channel Dimensions for Efficient Model Design](https://arxiv.org/abs/2007.00992), CVPR, 2020\n- [x] [`Xception`](cvm/models/xception.py) - [Xception: Deep Learning with Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357), CVPR, 2016\n- [x] [`DenseNet`](cvm/models/densenet.py) - [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993), CVPR, 2016\n- [ ] `DLA` - [Deep Layer Aggregation](https://arxiv.org/abs/1707.06484), CVPR, 2017\n- [ ] `DPN` - [Dual Path Networks](https://arxiv.org/abs/1707.01629), NeurIPS, 2017\n- [ ] `NASNet-A` - [Learning Transferable Architectures for Scalable Image Recognition](https://arxiv.org/abs/1707.07012), CVPR, 2017\n- [ ] `PNasNet` - [Progressive Neural Architecture Search](https://arxiv.org/abs/1712.00559), ECCV, 2017\n- [x] [`MobileNets`](cvm/models/mobilenet.py) - [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://arxiv.org/abs/1704.04861), 2017\n- [x] [`MobileNetV2`](cvm/models/mobilenetv2.py) - [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381), CVPR, 2018\n- [x] [`MobileNetV3`](cvm/models/mobilenetv3.py) - [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244), ICCV, 2019\n- [x] [`ShuffleNet`](cvm/models/shufflenet.py) - [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://arxiv.org/abs/1707.01083), CVPR, 2017\n- [x] [`ShuffleNetV2`](cvm/models/shufflenetv2.py) - [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://arxiv.org/abs/1807.11164), ECCV, 2018\n- [x] [`MnasNet`](cvm/models/mnasnet.py) - [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://arxiv.org/abs/1807.11626), CVPR, 2018\n- [x] [`GhostNet`](cvm/models/ghostnet.py) - [GhostNet: More Features from Cheap Operations](https://arxiv.org/abs/1911.11907), CVPR, 2019\n- [ ] `HRNet` - [Deep High-Resolution Representation Learning for Visual Recognition](https://arxiv.org/abs/1908.07919), TPAMI, 2019\n- [ ] `CSPNet` - [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://arxiv.org/abs/1911.11929), CVPR, 2019\n- [x] [`EfficientNet`](cvm/models/efficientnet.py) - [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946), ICML, 2019\n- [x] [`EfficientNetV2`](cvm/models/efficientnetv2.py) - [EfficientNetV2: Smaller Models and Faster Training](https://arxiv.org/abs/2104.00298), ICML, 2021\n- [x] [`RegNet`](cvm/models/regnet.py) - [Designing Network Design Spaces](https://arxiv.org/abs/2003.13678), CVPR, 2020\n- [ ] `GPU-EfficientNets` - [Neural Architecture Design for GPU-Efficient Networks](https://arxiv.org/abs/2006.14090), 2020\n- [ ] `LambdaNetworks` - [LambdaNetworks: Modeling Long-Range Interactions Without Attention](https://arxiv.org/abs/2102.08602), ICLR, 2021\n- [ ] `RepVGG` - [RepVGG: Making VGG-style ConvNets Great Again](https://arxiv.org/abs/2101.03697), CVPR, 2021\n- [ ] `HardCoRe-NAS` - [HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search](https://arxiv.org/abs/2102.11646), ICML, 2021\n- [ ] `NFNet` - [High-Performance Large-Scale Image Recognition Without Normalization](https://arxiv.org/abs/2102.06171), ICML, 2021\n- [ ] `NF-ResNets` - [Characterizing signal propagation to close the performance gap in unnormalized ResNets](https://arxiv.org/abs/2101.08692), ICLR, 2021\n- [x] [`ConvMixer`](cvm/models/convmixer.py) - [Patches are all you need?](https://openreview.net/forum?id=TVHS5Y4dNvM), 2021\n- [x] [`VGNets`](cvm/models/vgnet.py) - [Efficient CNN Architecture Design Guided by Visualization](https://arxiv.org/abs/2207.10318), ICME, 2022\n- [x] [`ConvNeXt`](cvm/models/convnext.py) - [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545), CVPR, 2022\n\n### Attention Blocks\n\n- [x] [`Non-Local`](cvm/models/ops/blocks/non_local.py) - [Non-local Neural Networks](https://arxiv.org/abs/1711.07971), CVPR, 2017\n- [x] [`Squeeze-and-Excitation`](cvm/models/ops/blocks/squeeze_excite.py) - [Squeeze-and-Excitation Networks](https://arxiv.org/abs/1709.01507), CVPR, 2017\n- [x] [`Gather-Excite`](cvm/models/ops/blocks/gather_excite.py) - [Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks](https://arxiv.org/abs/1810.12348), NeurIPS, 2018\n- [x] [`CBAM`](cvm/models/ops/blocks/cbam.py) - [CBAM: Convolutional Block Attention Module](https://arxiv.org/abs/1807.06521), ECCV, 2018\n- [x] [`SelectiveKernel`](cvm/models/ops/blocks/selective_kernel.py) - [Selective Kernel Networks](https://arxiv.org/abs/1903.06586), CVPR, 2019\n- [x] [`ECA`](cvm/models/ops/blocks/efficient_channel_attention.py) - [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://arxiv.org/abs/1910.03151), CVPR, 2019\n- [x] [`GlobalContext`](cvm/models/ops/blocks/global_context.py) - [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://arxiv.org/abs/1904.11492), 2019\n- [ ] `ResNeSt` - [ResNeSt: Split-Attention Networks](https://arxiv.org/abs/2004.08955), 2020\n- [ ] `HaloNets` - [Scaling Local Self-Attention for Parameter Efficient Visual Backbones](https://arxiv.org/abs/2103.12731), 2021\n\n### Transformer\n\n- [x] [`ViT`](cvm/models/vision_transformer.py) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929), ICLR, 2020\n- [ ] `DeiT` - [Training data-efficient image transformers \u0026 distillation through attention](https://arxiv.org/abs/2012.12877), ICML, 2020\n- [ ] `Swin Transformer` - [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030), ICCV, 2021\n- [ ] `Twins` - [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://arxiv.org/abs/2104.13840), NeurIPS, 2021\n\n### MLP\n\n- [x] [`MLP-Mixer`](cvm/models/mlp_mixer.py) - [MLP-Mixer: An all-MLP Architecture for Vision](https://arxiv.org/abs/2105.01601), NeurIPS, 2021\n- [x] [`ResMLP`](cvm/models/resmlp.py) - [ResMLP: Feedforward networks for image classification with data-efficient training](https://arxiv.org/abs/2105.03404), 2021\n- [ ] `gMLP` - [Pay Attention to MLPs](https://arxiv.org/abs/2105.08050), 2021\n\n### Self-supervised\n\n- [ ] `MAE` - [Masked Autoencoders Are Scalable Vision Learners](https://arxiv.org/abs/2111.06377), CVPR, 2021\n\n## Object Detection\n\n- [ ] `R-CNN` - [Rich feature hierarchies for accurate object detection and semantic segmentation](https://arxiv.org/abs/1311.2524), CVPR, 2013\n- [ ] `Fast R-CNN` - [Fast R-CNN](https://arxiv.org/abs/1504.08083), ICCV, 2015\n- [ ] `Faster R-CNN` - [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://arxiv.org/abs/1506.01497), 2015\n- [x] `YOLOv1` - [You Only Look Once: Unified, Real-Time Object Detection](https://arxiv.org/abs/1506.02640), 2015\n- [ ] `SSD` - [SSD: Single Shot MultiBox Detector](https://arxiv.org/abs/1512.02325), ECCV, 2015\n- [ ] `FPN` - [Feature Pyramid Networks for Object Detection](https://arxiv.org/abs/1612.03144), 2016\n\n## Semantic Segmentation\n\n- [x] [`FCN`](cvm/models/seg/fcn.py) - [Fully Convolutional Networks for Semantic Segmentation](https://arxiv.org/abs/1411.4038), CVPR, 2014\n- [x] [`UNet`](cvm/models/seg/unet.py) - [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597), MICCAI, 2015\n- [ ] `PSPNet` - [Pyramid Scene Parsing Network](https://arxiv.org/abs/1612.01105), CVPR, 2016\n- [x] [`DeepLabv3`](cvm/models/seg/deeplabv3.py) - [Rethinking Atrous Convolution for Semantic Image Segmentation](https://arxiv.org/pdf/1706.05587.pdf), 2017\n- [x] [`DeepLabv3+`](cvm/models/seg/deeplabv3_plus.py) - [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://arxiv.org/pdf/1802.02611.pdf), CVPR, 2018\n- [ ] `Mask R-CNN` - [Mask R-CNN](https://arxiv.org/abs/1703.06870), 2017\n\n## Generative Models\n\n### GANs\n\n- [x] `GAN` - [Generative Adversarial Networks](https://arxiv.org/abs/1406.2661), 2014\n- [x] [`DCGAN`](cvm/models/gan/dcgan.py) - [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://arxiv.org/abs/1511.06434), ICLR, 2016\n- [ ] `WGAN` - [Wasserstein GAN](https://arxiv.org/abs/1701.07875), 2017\n\n### VAEs\n\n- [x] [`VAE`](cvm/models/vae/vae.py) - [Auto-Encoding Variational Bayes](https://arxiv.org/abs/1312.6114), 2013\n- [x] [`CVAE`](cvm/models/vae/cvae.py) - [Learning Structured Output Representation using Deep Conditional Generative Models\n](https://papers.nips.cc/paper/2015/hash/8d55a249e6baa5c06772297520da2051-Abstract.html), NeurIPS, 2015\n- [ ] `β-VAE` - [beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework](https://openreview.net/forum?id=Sy2fzU9gl), ICLR, 2017\n\n\n### Diffusion Models\n\n\n### Flow-based\n\n\n## Adversarial Attacks\n\n - [x] [`FGSM`](cvm/attacks/fgsm.py) - [Explaining and Harnessing Adversarial Examples](https://arxiv.org/abs/1412.6572), ICLR, 2014\n - [x] [`PGD`](cvm/attacks/pgd.py) - [Towards Deep Learning Models Resistant to Adversarial Attacks](https://arxiv.org/abs/1706.06083), ICLR, 2017","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fffiirree%2Fcv-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fffiirree%2Fcv-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fffiirree%2Fcv-models/lists"}