{"id":26134345,"url":"https://github.com/kevinwood15/python_ml_neuralnetwork_project","last_synced_at":"2026-05-05T15:39:35.285Z","repository":{"id":281248368,"uuid":"944690056","full_name":"kevinwood15/Python_ML_NeuralNetwork_Project","owner":"kevinwood15","description":"I build a neural network to evaluate the CIFAR-10 dataset and achieve above 50% accuracy","archived":false,"fork":false,"pushed_at":"2025-03-07T19:53:41.000Z","size":0,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-07T20:32:56.113Z","etag":null,"topics":["cifar10","data-science","data-visualization","deep-learning","neural-network","python","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/kevinwood15.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":"2025-03-07T19:46:38.000Z","updated_at":"2025-03-07T19:56:50.000Z","dependencies_parsed_at":"2025-03-07T20:32:58.148Z","dependency_job_id":"f92abb0a-3e87-4c8e-94b2-7c06ac9c493e","html_url":"https://github.com/kevinwood15/Python_ML_NeuralNetwork_Project","commit_stats":null,"previous_names":["kevinwood15/python_neuralnetwork_project"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kevinwood15%2FPython_ML_NeuralNetwork_Project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kevinwood15%2FPython_ML_NeuralNetwork_Project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kevinwood15%2FPython_ML_NeuralNetwork_Project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kevinwood15%2FPython_ML_NeuralNetwork_Project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kevinwood15","download_url":"https://codeload.github.com/kevinwood15/Python_ML_NeuralNetwork_Project/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242945837,"owners_count":20210762,"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":["cifar10","data-science","data-visualization","deep-learning","neural-network","python","pytorch"],"created_at":"2025-03-11T00:00:09.270Z","updated_at":"2026-05-05T15:39:35.254Z","avatar_url":"https://github.com/kevinwood15.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Python_NeuralNetwork_Project\nIn this project, I use PyTorch to build a neural network and evaluate the CIFAR-10 dataset. \n\nI load the data, flatten the images, and specify a Cross Entropy loss function and Stochastic Gradient Descent optimizer. \nI train the data on a GPU accessible through Udacity, since this modeling is computationally intensive. I run 30 epochs until the test accuracy converges to around 50% (achieved at about epoch 22).\nThe testing loss and validation loss began to diverge around 15 to 30 epochs with an accuracy of 45%, so the model overfits to some extent. \n\nOverall, The model is a simple application of deep learning to image classification. I simply converted my images to tensors rather than specifying a more complication transformation with normalization, etc. \nPursuing these more compliated transformation could improve accuracy.\n\nMy model has 5 layers, starting with an input of 3072 (3x32x32 from the tensor dimensions) and reducing down to the 10 outputs, one for each class of image. \nEach layer utilizes a rectified linear unit function. I specified a cross entropy loss function and utilized stochastic gradient descent with a learning rate of 0.1. \nThe model could be improved with a more granular learning rate (for example 0.01, 0.001, ...), but this would involve more computational power.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkevinwood15%2Fpython_ml_neuralnetwork_project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkevinwood15%2Fpython_ml_neuralnetwork_project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkevinwood15%2Fpython_ml_neuralnetwork_project/lists"}