{"id":15664202,"url":"https://github.com/deep-diver/vgg","last_synced_at":"2025-05-06T18:49:38.666Z","repository":{"id":82125204,"uuid":"144690454","full_name":"deep-diver/VGG","owner":"deep-diver","description":"VGG models from ILSVRC 2014","archived":false,"fork":false,"pushed_at":"2022-10-16T03:30:29.000Z","size":278,"stargazers_count":4,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-31T01:51:17.027Z","etag":null,"topics":["cifar-10","cifar-100","convolutional-neural-networks","tensorflow","vggnet"],"latest_commit_sha":null,"homepage":"https://arxiv.org/pdf/1409.1556.pdf","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/deep-diver.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2018-08-14T08:20:34.000Z","updated_at":"2019-07-25T08:17:39.000Z","dependencies_parsed_at":"2023-03-12T14:51:59.664Z","dependency_job_id":null,"html_url":"https://github.com/deep-diver/VGG","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/deep-diver%2FVGG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deep-diver%2FVGG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deep-diver%2FVGG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deep-diver%2FVGG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/deep-diver","download_url":"https://codeload.github.com/deep-diver/VGG/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252750048,"owners_count":21798641,"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":["cifar-10","cifar-100","convolutional-neural-networks","tensorflow","vggnet"],"created_at":"2024-10-03T13:41:38.129Z","updated_at":"2025-05-06T18:49:38.647Z","avatar_url":"https://github.com/deep-diver.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# VGGs in TensorFlow\n\nThis repository comes with VGG implementation in TensorFlow. VGG took the 2nd place of the ILSVRC-2014 Competition.\n\nCurrently, the VGG models in this repo have been tested with CIFAR-10 and CIFAR-100 dataset. As an indivisual deep learner, it is hard to manage such a huge dataset, ImageNet. However, I will keep working on the ImageNet dataset, please wait for it.\n\n![VGG16](https://heuritech.files.wordpress.com/2016/02/vgg16.png?w=940)\nVGG16 model example figure from [Ref.](https://blog.heuritech.com/2016/02/29/a-brief-report-of-the-heuritech-deep-learning-meetup-5/)\n\n\u003e **VGG:** Visual Geometry Group @Oxford University\n\n## Required Packages\n- scikit-images\n- pickle\n- tqdm\n- numpy\n- tensorflow-gpu (\u003e1.7)\n\n## Usage\n- From command line\n  - Will download CIFAR-10 or CIFAR-100 dataset and pre-process of it, and run the training on VGG. It will produce the checkpoint file for performing inference later.\n```\npython vgg.py --model-type ['A'|'A-LRN'|'B'|'C'|'D'|'E'] --dataset ['cifar10'|'cifar100']\n```\n\n- From source code\n```python\nimport cifar10_utils\nimport cifar100_utils\nfrom vgg import VGG\n\n...\nvalid_set = (valid_features, valid_labels)\n...\n\n# model type, D is the most well known VGG16 without 1D conv layer\n# check the bottom section to see what model types are supported\nvggNet = VGG(dataset='cifar10', model_type='D', learning_rate=0.0001)\nvggNet.train(epochs=10, \n              batch_size=128, \n              valid_set=valid_set, \n              save_model_path='./model')\n```\n\n## Experiment on CIFAR-10 dataset (Not Yet Tested)\n- Environment\n  - Floydhub GPU2 instance (1 x Tesla V100)\n\n## Configurations\n- **A :** 11 weight layers\n- **A-LRN :** 11 weight layers with Local Response Normalization\n- **B :** 13 weight layers\n- **C :** 16 weight layers with 1D conv layers \n- **D :** 16 weight layers\n- **E :** 19 weight layers\n\n![Configuration](./models.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeep-diver%2Fvgg","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeep-diver%2Fvgg","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeep-diver%2Fvgg/lists"}