{"id":16887764,"url":"https://github.com/ethanhe42/resnet-imagenet-caffe","last_synced_at":"2025-04-13T09:43:18.957Z","repository":{"id":109158162,"uuid":"70119693","full_name":"ethanhe42/resnet-imagenet-caffe","owner":"ethanhe42","description":"train resnet on imagenet from scratch with caffe","archived":false,"fork":false,"pushed_at":"2022-02-09T20:48:51.000Z","size":1539,"stargazers_count":112,"open_issues_count":4,"forks_count":160,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-04-13T06:54:06.362Z","etag":null,"topics":["caffe","deep-learning","image-classification","imagenet","recoginition","resnet"],"latest_commit_sha":null,"homepage":"https://yihui-he.github.io/resnet-imagenet-caffe/","language":"Shell","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/ethanhe42.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null},"funding":{"github":null,"patreon":null,"open_collective":null,"ko_fi":"yihuihe","tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"lfx_crowdfunding":null,"custom":null}},"created_at":"2016-10-06T03:32:30.000Z","updated_at":"2023-12-18T16:08:09.000Z","dependencies_parsed_at":"2023-03-14T22:15:34.538Z","dependency_job_id":null,"html_url":"https://github.com/ethanhe42/resnet-imagenet-caffe","commit_stats":{"total_commits":30,"total_committers":2,"mean_commits":15.0,"dds":"0.19999999999999996","last_synced_commit":"058e2a0c6e40ee48620f279ce98f5e861283d12c"},"previous_names":["ethanhe42/resnet-imagenet-caffe"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethanhe42%2Fresnet-imagenet-caffe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethanhe42%2Fresnet-imagenet-caffe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethanhe42%2Fresnet-imagenet-caffe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ethanhe42%2Fresnet-imagenet-caffe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ethanhe42","download_url":"https://codeload.github.com/ethanhe42/resnet-imagenet-caffe/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248693907,"owners_count":21146885,"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":["caffe","deep-learning","image-classification","imagenet","recoginition","resnet"],"created_at":"2024-10-13T16:46:45.480Z","updated_at":"2025-04-13T09:43:18.933Z","avatar_url":"https://github.com/ethanhe42.png","language":"Shell","funding_links":["https://ko-fi.com/yihuihe"],"categories":[],"sub_categories":[],"readme":"# ResNet on ImageNet with Caffe\n\n[GitHub - yihui-he/resnet-imagenet-caffe: train resnet on imagenet from scratch with caffe](https://github.com/yihui-he/resnet-imagenet-caffe)\n\nAll models are trained on 4 GPUs with a minibatch size of 128. Testing is turned off during training due to memory limit(at least 12GB is require). The LMDB data is obtained from the [official caffe imagenet tutorial](http://caffe.berkeleyvision.org/gathered/examples/imagenet.html)\n\nTo train a network, use train.sh. For example, train resnet-50 with gpu 0,1,2,3:\n\n```bash\n#set caffe path in train.sh\nmkdir resnet_50/logs\nmkdir resnet_50/snapshot\n./train.sh 0,1,2,3 resnet_50 resnet_50_\n```\n\n**For better training results, please install [my Caffe fork](https://github.com/yihui-he/caffe-pro), since the official Caffe ImageData layer doesn’t support original paper’s augmentation (resize shorter side to 256 then crop to 224x224). Use my 224x224 mean image `bgr.binaryproto` accordinglySee `resnet_50/ResNet-50-test.prototxt` ImageData layer for details**\n\n### Citation\n\nIf you find the code useful in your research, please consider citing:\n\n```\n@InProceedings{He_2017_ICCV,\nauthor = {He, Yihui and Zhang, Xiangyu and Sun, Jian},\ntitle = {Channel Pruning for Accelerating Very Deep Neural Networks},\nbooktitle = {The IEEE International Conference on Computer Vision (ICCV)},\nmonth = {Oct},\nyear = {2017}\n}\n```\n\n### resnet-50\n\nuse `resnet_50/ResNet-50-test.prototxt` for training and validation\n\n(new) We’ve release a [2X accelerated ResNet-50](https://github.com/yihui-he/channel-pruning/releases/tag/ResNet-50-2X) caffemodel using [channel-pruning](https://github.com/yihui-he/channel-pruning)\n\n[](https://yihui-he.github.io/blog/channel-pruning-for-accelerating-very-deep-neural-networks)\n\n### resnet-32 This is a bottleneck architecture,\n\nSince there’s no strong data augmentation and 10-crop test in caffe, the results maybe a bit low.\n\ntest accuracy: accuracy@1 = 0.67892, accuracy@5 = 0.88164\n\ntraining loss for resnet-32 is shown below:\n\nthe trained model is provided in [release](https://github.com/yihui-he/resnet-imagenet-caffe/releases/download/v1.0/resnet_32_iter_750000.caffemodel)\n\n![https://raw.githubusercontent.com/yihui-he/resnet-imagenet-caffe/master/resnet_32/loss.png](https://raw.githubusercontent.com/yihui-he/resnet-imagenet-caffe/master/resnet_32/loss.png)\n\n### Other models on Caffe\n\n[](https://yihui-he.github.io/blog/resnet-on-cifar-10-with-caffe)\n\n[](https://yihui-he.github.io/blog/xception-with-caffe)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fethanhe42%2Fresnet-imagenet-caffe","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fethanhe42%2Fresnet-imagenet-caffe","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fethanhe42%2Fresnet-imagenet-caffe/lists"}