{"id":21030549,"url":"https://github.com/imdeep2905/digit-recognizer","last_synced_at":"2025-03-13T19:25:33.307Z","repository":{"id":52406956,"uuid":"249358138","full_name":"imdeep2905/Digit-Recognizer","owner":"imdeep2905","description":"This is a little project which implements ML model (trained on \"Hello World of ML\" - MNIST Digit Dataset) in real life. ","archived":false,"fork":false,"pushed_at":"2021-04-29T22:23:29.000Z","size":24020,"stargazers_count":3,"open_issues_count":1,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-20T15:19:05.571Z","etag":null,"topics":["convolutional-neural-network","deep-learning","keras","mnist-classification","mnist-handwriting-recognition","opencv-python","python","tensorflow","tkinter"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/imdeep2905.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-03-23T07:01:16.000Z","updated_at":"2020-07-16T20:44:07.000Z","dependencies_parsed_at":"2022-08-26T09:52:07.725Z","dependency_job_id":null,"html_url":"https://github.com/imdeep2905/Digit-Recognizer","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/imdeep2905%2FDigit-Recognizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imdeep2905%2FDigit-Recognizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imdeep2905%2FDigit-Recognizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/imdeep2905%2FDigit-Recognizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/imdeep2905","download_url":"https://codeload.github.com/imdeep2905/Digit-Recognizer/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243466988,"owners_count":20295310,"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":["convolutional-neural-network","deep-learning","keras","mnist-classification","mnist-handwriting-recognition","opencv-python","python","tensorflow","tkinter"],"created_at":"2024-11-19T12:18:59.662Z","updated_at":"2025-03-13T19:25:33.274Z","avatar_url":"https://github.com/imdeep2905.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Digit-Recognizer\n![Demo](https://github.com/imdeep2905/Digit-Recognizer/blob/master/Images/demo.gif)\u003cbr\u003e\n# Contents\n1. [Introduction](#Introduction)\n2. [How to run](#How-to-run) \n3. [For ML nerds](#For-all-ML-nerds)\n4. [Credits](#Credits)\n# Introduction\nThis is a little project which implements ML model (trained on **\"Hello World of ML\" - MNIST Digit Dataset**) in real life. You can hand draw digit in GUI, Browse an exsisting image and open your webcam and capture digit. Although model is really unstable with noisy images.(Maybe i'll try to improve it in future.)\u003cbr\u003e\nSome screenshots of Digit Recognizer:\u003cbr\u003e\n![Main Screen](https://github.com/imdeep2905/Digit-Recognizer/blob/master/Images/mainscreen.PNG)\u003cbr\u003e\n![Main Screen2](https://github.com/imdeep2905/Digit-Recognizer/blob/master/Images/mainscreen2.PNG)\u003cbr\u003e\n![Main Screen3](https://github.com/imdeep2905/Digit-Recognizer/blob/master/Images/mainscreen3.PNG)\u003cbr\u003e\n\n# How to run\n  1. Fulfill ```requirements.txt``` (i.e. ```pip install -r requirements.txt```).\n  2. Run with command ```python main.py```.\n\n# For all ML nerds\nFor all the ML nerds out there model was trained on following architecture:\n```\nmodel = keras.models.Sequential([\nkeras.layers.Conv2D(64, (2, 2), padding = 'same' , activation = 'elu', input_shape = [28, 28, 1]),\nkeras.layers.MaxPooling2D(2),\nkeras.layers.Conv2D(128, (3, 3), padding = \"same\", activation = \"elu\"),\nkeras.layers.Conv2D(256, (4, 4), padding = \"same\", activation = \"elu\"),\nkeras.layers.Dropout(0.5),\nkeras.layers.MaxPooling2D(2),\nkeras.layers.Flatten(),\nkeras.layers.Dense(128, activation = \"elu\"),\nkeras.layers.Dropout(0.25),\nkeras.layers.Dense(10, activation = \"softmax\")\n])\n\nmodel.compile(loss = \"sparse_categorical_crossentropy\", metrics = [\"accuracy\"], optimizer = keras.optimizers.SGD(lr = 0.08))\n``` \nIt's accuracy was around ```0.99``` on training data and ```0.95-0.97(not sure)``` on testing data.\u003cbr\u003e\nAt last you can load pretrained model (```model.h5```) and play with it.\n\n# Credits\n\nContributors :computer: : \n   * [Deep Raval](https://github.com/imdeep2905)\n\nWithout these excellant libraries :heart: this would not have been possible.\n   * tensorflow\n   * pillow\n   * opencv-python\n   * numpy\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimdeep2905%2Fdigit-recognizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fimdeep2905%2Fdigit-recognizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimdeep2905%2Fdigit-recognizer/lists"}