{"id":18433150,"url":"https://github.com/ramesh-x/mnist-cnn","last_synced_at":"2026-04-29T09:35:48.322Z","repository":{"id":122414228,"uuid":"105970436","full_name":"Ramesh-X/MNIST-CNN","owner":"Ramesh-X","description":"CNN with Inception modules for MNIST classifier","archived":false,"fork":false,"pushed_at":"2017-10-17T04:43:47.000Z","size":19798,"stargazers_count":0,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-16T09:28:40.682Z","etag":null,"topics":["cnn","inception-module","mnist-classification","python","tensorflow"],"latest_commit_sha":null,"homepage":"","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/Ramesh-X.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":"2017-10-06T05:30:01.000Z","updated_at":"2018-03-01T13:36:30.000Z","dependencies_parsed_at":null,"dependency_job_id":"591d9928-6dfc-46bc-ad39-472c633989b3","html_url":"https://github.com/Ramesh-X/MNIST-CNN","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/Ramesh-X%2FMNIST-CNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ramesh-X%2FMNIST-CNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ramesh-X%2FMNIST-CNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ramesh-X%2FMNIST-CNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ramesh-X","download_url":"https://codeload.github.com/Ramesh-X/MNIST-CNN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248812254,"owners_count":21165393,"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":["cnn","inception-module","mnist-classification","python","tensorflow"],"created_at":"2024-11-06T05:32:06.006Z","updated_at":"2026-04-29T09:35:43.295Z","avatar_url":"https://github.com/Ramesh-X.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CNN with Inception Modules for MNIST dataset\n\nClassification of MNIST digits by convolutional neural networks (CNN) with Dropout and Inception layers.\nNo preprocessing done.\n\nThe code is written using Tenserflow.\n\nUsed in Digit Recognizer competition on Kaggle https://www.kaggle.com/c/digit-recognizer\n\n## Network architecture\n\n| Layer Type| Kernel Size / Stride | Output Size | #1×1 | #3×3 reduce | #3×3 | #5×5 reduce | #5×5 | pool proj |\n| :--:      | :--:                 | :--:        | :--:        | :--: | :--: | :--:        | :--: | :--: |\n| Input     | -                    | 28x28x1     |    |   |   |   |   |   |\n| Conv      | 5 x 5 / 1            | 28x28x64    |    |   |   |   |64 |   |\n| Conv      | 3 x 3 / 1            | 28x28x128   |    |   |128|   |   |   |\n| MaxPool   | 3 x 3 / 2            | 14x14x128   |    |   |   |   |   |   |\n| Norm      |                      | 14x14x128   |    |   |   |   |   |   |\n| Inception |                      | 14x14x128   |  8 |64 |96 |8  |16 |8  |\n| Inception |                      | 14x14x256   |64  |96 |128|16 |32 |32 |\n| Inception |                      | 14x14x512   |160 |112|224|24 |64 |64 |\n| MaxPool   | 3 x 3 / 2            | 7x7x512     |    |   |   |   |   |   |\n| Norm      |                      | 7x7x512     |    |   |   |   |   |   |\n| Inception |                      | 7x7x512     |128 |128|256|32 |64 |64 |\n| AvgPool   | 7 x 7 / 7            | 1x1x512     |    |   |   |   |   |   |\n| Dropout   |                      | 1x1x512     |    |   |   |   |   |   |\n| FC        |                      | 1x1x10      |    |   |   |   |   |   |\n| Softmax   |                      | 1x1x10      |    |   |   |   |   |   |\n\nAccuracy of the model: **0.99261** with my test set and **0.99428** in Kaggle competition.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Framesh-x%2Fmnist-cnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Framesh-x%2Fmnist-cnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Framesh-x%2Fmnist-cnn/lists"}