{"id":24098473,"url":"https://github.com/matlab-deep-learning/resnet-101","last_synced_at":"2025-10-11T18:15:04.635Z","repository":{"id":118345462,"uuid":"214175420","full_name":"matlab-deep-learning/resnet-101","owner":"matlab-deep-learning","description":"Repo for ResNet-101 model","archived":false,"fork":false,"pushed_at":"2019-10-10T12:22:47.000Z","size":125,"stargazers_count":13,"open_issues_count":0,"forks_count":5,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-05-07T19:47:39.403Z","etag":null,"topics":["deep-learning","matlab","matlab-deep-learning","pretrained-models"],"latest_commit_sha":null,"homepage":"","language":"MATLAB","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/matlab-deep-learning.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2019-10-10T12:20:43.000Z","updated_at":"2024-12-03T22:19:17.000Z","dependencies_parsed_at":"2023-11-05T19:00:32.165Z","dependency_job_id":null,"html_url":"https://github.com/matlab-deep-learning/resnet-101","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/matlab-deep-learning/resnet-101","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab-deep-learning%2Fresnet-101","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab-deep-learning%2Fresnet-101/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab-deep-learning%2Fresnet-101/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab-deep-learning%2Fresnet-101/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/matlab-deep-learning","download_url":"https://codeload.github.com/matlab-deep-learning/resnet-101/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab-deep-learning%2Fresnet-101/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262393076,"owners_count":23304041,"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":["deep-learning","matlab","matlab-deep-learning","pretrained-models"],"created_at":"2025-01-10T14:46:11.779Z","updated_at":"2025-10-11T18:14:59.596Z","avatar_url":"https://github.com/matlab-deep-learning.png","language":"MATLAB","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Overview\r\n\r\nResNet-101 is a convolutional neural network that is trained on more than a million images from the ImageNet database. As a result, the network has learned rich feature representations for a wide range of images. The network can classify images into 1000 object categories, such as keyboard, mouse, pencil, and many animals.\r\n\r\nThe network has an image input size of 224-by-224-by-3. \r\n\r\n# Usage\r\n\r\nThis repository requires [MATLAB](https://www.mathworks.com/products/matlab.html) (R2018b and above) and the [Deep Learning Toolbox](https://www.mathworks.com/products/deep-learning.html).\r\n\r\nThis repository provides three functions:\r\n- resnet101Layers: Creates an untrained network with the network architecture of ResNet-101\r\n- assembleResNet101: Creates a ResNet-101 network with weights trained on ImageNet data\r\n- resnet101Example: Demonstrates how to classify an image using a trained ResNet-101 network\r\n\r\nTo construct an untrained ResNet-101 network to train from scratch, type the following at the MATLAB command line:\r\n```matlab\r\nlgraph = resnet101Layers;\r\n```\r\nThe untrained network is returned as a `layerGraph` object.\r\n\r\nTo construct a trained ResNet-101 network suitable for use in image classification, type the following at the MATLAB command line: \r\n```matlab\r\nnet = assembleResNet101;\r\n```\r\nThe trained network is returned as a `DAGNetwork` object.\r\n\r\nTo classify an image with the network:\r\n```matlab\r\nimg = imresize(imread(\"peppers.png\"),[224 224]);\r\npredLabel = classify(net, img);\r\nimshow(img);\r\ntitle(string(predLabel));\r\n```\r\n\r\n# Documentation\r\n\r\nFor more information about the ResNet-101 pre-trained model, see the [resnet101](https://www.mathworks.com/help/deeplearning/ref/resnet101.html) function page in the [MATLAB Deep Learning Toolbox documentation](https://www.mathworks.com/help/deeplearning/index.html).\r\n\r\n# Architecture\r\n\r\nResNet-101 is a residual network. A residual network is a type of DAG network that has residual (or shortcut) connections that bypass the main network layers. Residual connections enable the parameter gradients to propagate more easily from the output layer to the earlier layers of the network, which makes it possible to train deeper networks. This increased network depth can result in higher accuracies on more difficult tasks.\r\n\r\nThe network is 101 layers deep. The network depth is defined as the largest number of sequential convolutional or fully connected layers on a path from the input layer to the output layer. In total, ResNet-101 has 347 layers.\r\n\r\nYou can explore and edit the network architecture using [Deep Network Designer](https://www.mathworks.com/help/deeplearning/ug/build-networks-with-deep-network-designer.html).\r\n\r\n![ResNet-101 in Deep Network Designer](images/resnet101_deepNetworkDesigner.png \"ResNet-101 in Deep Network Designer\")\r\n\r\n# ResNet-101 in MATLAB\r\n\r\nThis repository demonstrates the construction of a residual deep neural network from scratch in MATLAB. You can use the code in this repository as a foundation for building residual networks with different numbers of residual blocks.\r\n\r\nYou can also create a trained ResNet-101 network from inside MATLAB by installing the Deep Learning Toolbox Model for ResNet-101 Network support package. Type `resnet101` at the command line. If the Deep Learning Toolbox Model for ResNet-101 Network support package is not installed, then the function provides a link to the required support package in the Add-On Explorer. To install the support package, click the link, and then click Install.\r\n\r\nAlternatively, you can download the ResNet-101 pre-trained model from the MathWorks File Exchange, at [Deep Learning Toolbox Model for ResNet-101 Network](https://www.mathworks.com/matlabcentral/fileexchange/65678-deep-learning-toolbox-model-for-resnet-101-network). \r\n\r\nYou can create an untrained ResNet-101 network from inside MATLAB by importing a trained ResNet-101 network into the Deep Network Designer App and selecting Export \u003e Generate Code. The exported code will generate an untrained network with the network architecture of ResNet-101.\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatlab-deep-learning%2Fresnet-101","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmatlab-deep-learning%2Fresnet-101","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatlab-deep-learning%2Fresnet-101/lists"}