{"id":24098469,"url":"https://github.com/matlab-deep-learning/resnet-50","last_synced_at":"2025-05-07T19:25:49.867Z","repository":{"id":41572981,"uuid":"238713483","full_name":"matlab-deep-learning/resnet-50","owner":"matlab-deep-learning","description":"Repo for ResNet-50","archived":false,"fork":false,"pushed_at":"2020-02-06T14:58:01.000Z","size":78,"stargazers_count":28,"open_issues_count":0,"forks_count":4,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-31T13:26:17.831Z","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}},"created_at":"2020-02-06T14:57:03.000Z","updated_at":"2025-01-27T14:56:06.000Z","dependencies_parsed_at":"2022-08-20T08:22:27.553Z","dependency_job_id":null,"html_url":"https://github.com/matlab-deep-learning/resnet-50","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/matlab-deep-learning%2Fresnet-50","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab-deep-learning%2Fresnet-50/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab-deep-learning%2Fresnet-50/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab-deep-learning%2Fresnet-50/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-50/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252942497,"owners_count":21829087,"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":"2025-01-10T14:46:07.707Z","updated_at":"2025-05-07T19:25:49.804Z","avatar_url":"https://github.com/matlab-deep-learning.png","language":"MATLAB","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Overview\n\nResNet-50 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.\n\nThe network has an image input size of 224-by-224-by-3. \n\n# Usage\n\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).\n\nThis repository provides three functions:\n- resnet50Layers: Creates an untrained network with the network architecture of ResNet-50\n- assembleResNet50: Creates a ResNet-50 network with weights trained on ImageNet data\n- resnet50Example: Demonstrates how to classify an image using a trained ResNet-50 network\n\nTo construct an untrained ResNet-50 network to train from scratch, type the following at the MATLAB command line:\n```matlab\nlgraph = resnet50Layers;\n```\nThe untrained network is returned as a `layerGraph` object.\n\nTo construct a trained ResNet-50 network suitable for use in image classification, type the following at the MATLAB command line: \n```matlab\nnet = assembleResNet50;\n```\nThe trained network is returned as a `DAGNetwork` object.\n\nTo classify an image with the network:\n```matlab\nimg = imresize(imread(\"peppers.png\"),[224 224]);\npredLabel = classify(net, img);\nimshow(img);\ntitle(string(predLabel));\n```\n\n# Documentation\n\nFor more information about the ResNet-50 pre-trained model, see the [resnet50](https://www.mathworks.com/help/deeplearning/ref/resnet50.html) function page in the [MATLAB Deep Learning Toolbox documentation](https://www.mathworks.com/help/deeplearning/index.html).\n\n# Architecture\n\nResNet-50 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.\n\nThe network is 50 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-50 has 177 layers.\n\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).\n\n![ResNet-50 in Deep Network Designer](images/resnet50_deepNetworkDesigner.PNG \"ResNet-50 in Deep Network Designer\")\n\n# ResNet-50 in MATLAB\n\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.\n\nYou can also create a trained ResNet-50 network from inside MATLAB by installing the Deep Learning Toolbox Model for ResNet-50 Network support package. Type `resnet50` at the command line. If the Deep Learning Toolbox Model for ResNet-50 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.\n\nAlternatively, you can download the ResNet-50 pre-trained model from the MathWorks File Exchange, at [Deep Learning Toolbox Model for ResNet-50 Network](https://www.mathworks.com/matlabcentral/fileexchange/64626-deep-learning-toolbox-model-for-resnet-50-network). \n\nYou can create an untrained ResNet-50 network from inside MATLAB by importing a trained ResNet-50 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-50.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatlab-deep-learning%2Fresnet-50","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmatlab-deep-learning%2Fresnet-50","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatlab-deep-learning%2Fresnet-50/lists"}