{"id":21394107,"url":"https://github.com/rucksikaar/color_initial_letter_recognition","last_synced_at":"2026-05-11T16:37:59.169Z","repository":{"id":209846496,"uuid":"725088238","full_name":"RucksikaaR/Color_Initial_Letter_Recognition","owner":"RucksikaaR","description":"Recognize handwritten letters with Neuton TinyML. This repository contains the C library (TinyML model) and the Arduino sketch file that can be used to embed the model in your microcontroller.","archived":false,"fork":false,"pushed_at":"2023-11-29T12:15:49.000Z","size":15,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-16T14:22:52.343Z","etag":null,"topics":["arduino","c","tinyml"],"latest_commit_sha":null,"homepage":"","language":"C","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/RucksikaaR.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-29T12:15:04.000Z","updated_at":"2023-11-29T12:21:02.000Z","dependencies_parsed_at":"2024-01-31T21:39:47.613Z","dependency_job_id":null,"html_url":"https://github.com/RucksikaaR/Color_Initial_Letter_Recognition","commit_stats":null,"previous_names":["rucksikaar/color_initial_letter_recognition"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/RucksikaaR/Color_Initial_Letter_Recognition","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RucksikaaR%2FColor_Initial_Letter_Recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RucksikaaR%2FColor_Initial_Letter_Recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RucksikaaR%2FColor_Initial_Letter_Recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RucksikaaR%2FColor_Initial_Letter_Recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RucksikaaR","download_url":"https://codeload.github.com/RucksikaaR/Color_Initial_Letter_Recognition/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RucksikaaR%2FColor_Initial_Letter_Recognition/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32903819,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-10T13:40:02.631Z","status":"online","status_checked_at":"2026-05-11T02:00:05.975Z","response_time":120,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["arduino","c","tinyml"],"created_at":"2024-11-22T14:14:26.133Z","updated_at":"2026-05-11T16:37:59.144Z","avatar_url":"https://github.com/RucksikaaR.png","language":"C","funding_links":[],"categories":[],"sub_categories":[],"readme":"# How to integrate Neuton into your firmware project \n\n## Include header file\n\nCopy all files from this archive to your project and include header file:\n``` C\n#include \"neuton.h\"\n```\n\nThe library contains functions to get model information such as:\n* task type (regression, classification, etc.);\n* neurons and weights count;\n* window buffer size;\n* input and output features count;\n* model size and RAM usage;\n* float support flag;\n* quantization level.\n\nMain functions are:\n* `neuton_model_set_inputs` - to set input values;\n* `neuton_model_run_inference` - to make predictions.\n\n\n## Set input values\n\nMake an array with model inputs. Inputs count and order should be the same as in the training dataset.\n\n``` C\ninput_t inputs[] = {\n    feature_0,\n    feature_1,\n    // ...\n    feature_N\n};\n```\n\nPass this array to `neuton_model_set_inputs` function. \n\nIf digital signal processing option was selected on the platform, you should call `neuton_model_set_inputs` multiple times for each sample to fill internal window buffer. Function will return `0` when buffer is full, this indicates that model is ready for prediction.\n\n\n##\tMake prediction\n\nWhen buffer is ready, you should call `neuton_model_run_inference` with two arguments:\n* pointer to `index` of predicted class;\n* pointer to neural net `outputs` (dimension of array can be read using `neuton_model_outputs_count` function).\n\nFor regression task output value will be stored at `outputs[0]`.\nFor classification task `index` will contain class index with maximal probability, `outputs` will contain probabilities of each class. Thus, you can get predicted class probability at `outputs[index]`.\n\nFunction will return `0` on successful prediction.\n``` C\nif (neuton_model_set_inputs(inputs) == 0)\n{\n    uint16_t index;\n    float* outputs;\n    \n    if (neuton_model_run_inference(\u0026index, \u0026outputs) == 0)\n    {\n        // code for handling prediction result\n    }\n}\n```\n\n## Map predicted results on the required values (for Classification task type)\n\nInference results are encoded (0…n). For mapping on your classes, use dictionaries `binary_target_dict_csv.csv / multi_target_dict_csv.csv`.\n\n##\tIntegration with Tensorflow, ONNX\n\nNeuton also offers additional options of integration and interaction with your model.\nThis archive provides you with Tensorflow and ONNX formats of the model.\nYou can find them in `converted_models` folder.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frucksikaar%2Fcolor_initial_letter_recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frucksikaar%2Fcolor_initial_letter_recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frucksikaar%2Fcolor_initial_letter_recognition/lists"}