{"id":13499051,"url":"https://github.com/songhan/SqueezeNet-Residual","last_synced_at":"2025-03-29T03:32:22.102Z","repository":{"id":119631405,"uuid":"56886463","full_name":"songhan/SqueezeNet-Residual","owner":"songhan","description":"residual-SqueezeNet","archived":false,"fork":false,"pushed_at":"2019-03-15T20:03:57.000Z","size":5194,"stargazers_count":154,"open_issues_count":2,"forks_count":67,"subscribers_count":19,"default_branch":"master","last_synced_at":"2024-10-31T17:39:10.931Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"CSS","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/songhan.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":"2016-04-22T21:33:00.000Z","updated_at":"2024-01-04T16:04:24.000Z","dependencies_parsed_at":null,"dependency_job_id":"7a4dbc46-c5eb-41b2-aef1-b91967446c64","html_url":"https://github.com/songhan/SqueezeNet-Residual","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/songhan%2FSqueezeNet-Residual","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/songhan%2FSqueezeNet-Residual/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/songhan%2FSqueezeNet-Residual/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/songhan%2FSqueezeNet-Residual/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/songhan","download_url":"https://codeload.github.com/songhan/SqueezeNet-Residual/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":"2024-07-31T22:00:27.589Z","updated_at":"2025-03-29T03:32:21.561Z","avatar_url":"https://github.com/songhan.png","language":"CSS","funding_links":[],"categories":["Papers\u0026Codes"],"sub_categories":["SqueezeNet"],"readme":"- March 15, 2019: for our most updated work on model compression and acceleration, please reference: \n\n\t[ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://arxiv.org/pdf/1812.00332.pdf) (ICLR’19)\n\n\t[AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://arxiv.org/pdf/1802.03494.pdf) (ECCV’18)\n\n\t[HAQ: Hardware-Aware Automated Quantization](https://arxiv.org/pdf/1811.08886.pdf)  (CVPR’19)\n\t\n\t[Defenstive Quantization: When Efficiency Meets Robustness](https://openreview.net/pdf?id=ryetZ20ctX) (ICLR'19)\n    \n# SqueezeNet-Residual\n\nThe repo contains the residual-SqueezeNet, which is obtained by adding bypass layer to SqueezeNet_v1.0. Residual-SqueezeNet improves the top-1 accuracy of SqueezeNet by 2.9% on ImageNet without changing the model size(only 4.8MB).\n\n# Related repo and paper\n[SqueezeNet](https://github.com/DeepScale/SqueezeNet)\n\n[SqueezeNet-Deep-Compression](https://github.com/songhan/SqueezeNet-Deep-Compression)\n\n[SqueezeNet-Generator](https://github.com/songhan/SqueezeNet-Generator)\n\n[SqueezeNet-DSD-Training](https://github.com/songhan/SqueezeNet-DSD-Training)\n\n[SqueezeNet-Residual](https://github.com/songhan/SqueezeNet-Residual)\n\n\n\nIf you find residual-SqueezeNet useful in your research, please consider citing the paper:\n\n    @article{SqueezeNet,\n      title={SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and\u003c 0.5MB model size},\n      author={Iandola, Forrest N and Han, Song and Moskewicz, Matthew W and Ashraf, Khalid and Dally, William J and Keutzer, Kurt},\n      journal={arXiv preprint arXiv:1602.07360},\n      year={2016}\n    }\n  \n\n# Usage\n\n    $CAFFE_ROOT/build/tools/caffe test --model=trainval.prototxt --weights=SqueezeNet_residual_top1_0.6038_top5_0.8250.caffemodel --iterations=1000 --gpu 0\n\n# Result\n      \n    I0422 14:07:39.810755 32299 caffe.cpp:293] accuracy_top1 = 0.603759\n    I0422 14:07:39.810775 32299 caffe.cpp:293] accuracy_top5 = 0.824981\n    I0422 14:07:39.810792 32299 caffe.cpp:293] loss = 1.76711 (* 1 = 1.76711 loss) \n    \n# Architecture of the residual SqueezeNet\n\u003cbr\u003e\n\u003cimg src=\"figure/architecture2.jpg\"  height=\"600px\" align=\"middle\" /\u003e\n\n\nThe building block:\n\n\n\u003cimg src=\"figure/type2.jpg\"  height=\"250px\" align=\"middle\"/\u003e\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsonghan%2FSqueezeNet-Residual","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsonghan%2FSqueezeNet-Residual","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsonghan%2FSqueezeNet-Residual/lists"}