{"id":21546483,"url":"https://github.com/gui-sitton/neuralnetwork","last_synced_at":"2026-04-13T16:01:45.004Z","repository":{"id":200577581,"uuid":"705842560","full_name":"Gui-Sitton/NeuralNetwork","owner":"Gui-Sitton","description":"The task is then to build and evaluate a model to verify people's ages You will have a set of photographs of people with their ages indicated.","archived":false,"fork":false,"pushed_at":"2023-11-30T18:48:35.000Z","size":4986,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-18T00:53:33.344Z","etag":null,"topics":["keras","keras-neural-networks","neural-network","python","tensorflow"],"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/Gui-Sitton.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":"2023-10-16T19:49:57.000Z","updated_at":"2023-11-30T18:47:37.000Z","dependencies_parsed_at":null,"dependency_job_id":"f92a7197-92ae-41ed-8290-d8a7ab733cb6","html_url":"https://github.com/Gui-Sitton/NeuralNetwork","commit_stats":null,"previous_names":["gui-sitton/neuralnetwork"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Gui-Sitton/NeuralNetwork","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gui-Sitton%2FNeuralNetwork","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gui-Sitton%2FNeuralNetwork/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gui-Sitton%2FNeuralNetwork/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gui-Sitton%2FNeuralNetwork/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Gui-Sitton","download_url":"https://codeload.github.com/Gui-Sitton/NeuralNetwork/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Gui-Sitton%2FNeuralNetwork/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31759540,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T15:25:13.801Z","status":"ssl_error","status_checked_at":"2026-04-13T15:25:09.162Z","response_time":93,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["keras","keras-neural-networks","neural-network","python","tensorflow"],"created_at":"2024-11-24T06:12:16.858Z","updated_at":"2026-04-13T16:01:44.983Z","avatar_url":"https://github.com/Gui-Sitton.png","language":"Jupyter Notebook","readme":"# NeuralNetwork\n\n## Intro\nThe Boa Semente supermarket chain would like to explore whether Data Science can help them follow alcohol laws, ensuring that they don't sell alcohol to minors. You are asked to carry out this assessment, so as you get to work, keep the following in mind:\nStores are equipped with cameras in the checkout area that are triggered when a person is buying alcohol\nComputer vision methods can be used to determine a person's age from a photo\nThe task is then to build and evaluate a model to verify people's ages\nYou will have a set of photographs of people with their ages indicated.\n\n### Project instructions\n* Perform an exploratory data analysis to get an overall impression of the data set.\n* Train and evaluate the model (needs to be done on the GPU platform).\n* Combine your code, output and findings (from the previous points) in the final Jupyter notebook.\n* Draw conclusions from the model evaluation, add them to the notebook.\n\n\n## Libraries used\n\nimport pandas as pd\n\nimport warnings\n\nwarnings.filterwarnings(\"ignore\", category=RuntimeWarning)\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\nimport plotly.express as px\n\nimport tensorflow as tf\n\nfrom tensorflow.keras.applications.resnet import ResNet50\n\nfrom tensorflow.keras.models import Sequential\n\nfrom tensorflow.keras.layers import GlobalAveragePooling2D, Dense, Dropout, Flatten\n\nfrom tensorflow.keras.optimizers import Adam\n\nimport inspect\n\n## Conclusion\n\nmae: 7.9925: MAE stands for Mean Absolute Error. It is an evaluation metric that indicates the average absolute difference between the model's predictions and the actual values. An MAE value of 7.9925 indicates that, on average, the model's predictions have an absolute error of approximately 7.99 units in relation to the actual values. The aim is to minimize this metric as much as possible\n\nTest MAE: 7.9925: This is the MAE metric calculated on the test set, which represents how well the model generalizes to data that was not used during training. An MAE value of 7.9925 indicates that, on average, the model's predictions on the test set have an absolute error of approximately 7.99 units with respect to the actual values.\n\nThe ResNet-50 model is making progress in training, with the loss decreasing over the epochs.\n\n**Model passes, mae below 8**\n\n# Rede Neural\n\n## Introdução\nA rede de supermercados Boa Semente gostaria de explorar se a ciência de dados pode ajudá-la a seguir as leis sobre bebidas alcoólicas, garantindo que não vendam bebidas alcoólicas para menores de idade. Você foi solicitado a realizar essa avaliação, portanto, ao começar a trabalhar, tenha em mente o seguinte:\nAs lojas são equipadas com câmeras na área do caixa que são acionadas quando uma pessoa está comprando álcool\nMétodos de visão computacional podem ser usados para determinar a idade de uma pessoa a partir de uma foto\nA tarefa é, então, criar e avaliar um modelo para verificar a idade das pessoas\nVocê terá um conjunto de fotografias de pessoas com suas idades indicadas.\n\n### Instruções do projeto\n* Realizar uma análise exploratória de dados para obter uma impressão geral do conjunto de dados.\n* Treinar e avaliar o modelo (precisa ser feito na plataforma GPU).\n* Combine seu código, resultados e descobertas (dos pontos anteriores) no notebook Jupyter final.\n* Tire conclusões da avaliação do modelo e adicione-as ao notebook.\n\n\n## Bibliotecas usadas\n\nimport pandas as pd\n\nimportar warnings\n\nwarnings.filterwarnings(\"ignore\", category=RuntimeWarning)\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\nimport plotly.express as px\n\nimport tensorflow as tf\n\nfrom tensorflow.keras.applications.resnet import ResNet50\n\nfrom tensorflow.keras.models import Sequential\n\nfrom tensorflow.keras.layers import GlobalAveragePooling2D, Dense, Dropout, Flatten\n\nfrom tensorflow.keras.optimizers import Adam\n\nimport inspect\n\n## Conclusão\n\nmae: 7,9925: MAE significa Mean Absolute Error (erro absoluto médio). É uma métrica de avaliação que indica a diferença absoluta média entre as previsões do modelo e os valores reais. Um valor de MAE de 7,9925 indica que, em média, as previsões do modelo têm um erro absoluto de aproximadamente 7,99 unidades em relação aos valores reais. O objetivo é minimizar essa métrica o máximo possível\n\nMAE de teste: 7,9925: Essa é a métrica MAE calculada no conjunto de teste, que representa o grau de generalização do modelo para dados que não foram usados durante o treinamento. Um valor MAE de 7,9925 indica que, em média, as previsões do modelo no conjunto de teste têm um erro absoluto de aproximadamente 7,99 unidades com relação aos valores reais.\n\nO modelo ResNet-50 está progredindo no treinamento, com a perda diminuindo ao longo das épocas.\n\n**O modelo é aprovado, com mae abaixo de 8**\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgui-sitton%2Fneuralnetwork","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgui-sitton%2Fneuralnetwork","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgui-sitton%2Fneuralnetwork/lists"}