{"id":22367256,"url":"https://github.com/yeyom/not_hotdog_model","last_synced_at":"2026-05-08T18:32:34.934Z","repository":{"id":134244498,"uuid":"591548940","full_name":"YeyoM/Not_Hotdog_Model","owner":"YeyoM","description":"In this notebook I will try to recreate a curious model used in an App shown in the HBO serie \"Sillicon Valley\". ","archived":false,"fork":false,"pushed_at":"2023-01-21T04:52:30.000Z","size":3039,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-01-31T17:14:08.405Z","etag":null,"topics":["keras","mobilenetv2","not-hotdog","sillicon-valey","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/YeyoM.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":"2023-01-21T03:43:56.000Z","updated_at":"2023-09-13T12:03:38.000Z","dependencies_parsed_at":null,"dependency_job_id":"3a1b0fa8-8a98-4765-a717-2830b7ee998d","html_url":"https://github.com/YeyoM/Not_Hotdog_Model","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/YeyoM%2FNot_Hotdog_Model","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeyoM%2FNot_Hotdog_Model/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeyoM%2FNot_Hotdog_Model/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YeyoM%2FNot_Hotdog_Model/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YeyoM","download_url":"https://codeload.github.com/YeyoM/Not_Hotdog_Model/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245689453,"owners_count":20656414,"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":["keras","mobilenetv2","not-hotdog","sillicon-valey","tensorflow"],"created_at":"2024-12-04T18:16:55.378Z","updated_at":"2026-05-08T18:32:34.899Z","avatar_url":"https://github.com/YeyoM.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Not_Hotdog_Model\n\nIn this notebook I will try to recreate a curious model used in an App shown in the HBO serie \"Sillicon Valley\". \n\nFor this model, I will use the hotdog-nothotdog dataset from Kaggle, and to build the model my way to go was to use Tensorflow using Keras layers to build a Convolutional Neural Network and a pre-trained model to make use of transfer learning from the mobileNet v2 model.\n\nAlong the notebook and the code blocks, I will try to explain as best as I can what the building process of this model works and at the end obviously the results I got.\n\nHopefully I can also build the App as in the serie with this model I built, which is the first model I built by my own.\n\nA detailed explanation of how the model was built take a look at the notebook attached in this repo.\n\nYou can found the google colab notebook in the following link:\n- https://colab.research.google.com/drive/1ScYoJsGa-C5tqyyR5ETeA7pAgXwtwCx1#scrollTo=R0za6i4K4hkg\n\nHere are the results I got.\n\n## Results\n\n### Training\n\nFor the training process I run it for 20 epochs, with a batch size of 32 and a learning rate of 0.0001. Using the mobileNet v2 and some more layers including dropout and image augmentation to prevent overfitting. The results I got were the following:\n\n[![training][training-screenshot]]()\n\n### Evaluation\n\nFor the evaluation process I used the validation set of the dataset and the results I got were the following:\n\n[![evaluate][evaluate-screenshot]]()\n\n### Predictions\n\nFor the predictions I used the test set of the dataset and the results I got were the following:\n\n[![predictions][predictions-screenshot]]()\n\n\n[training-screenshot]: public/training.png\n[evaluate-screenshot]: public/evaluate.png\n[predictions-screenshot]: public/predictions.png\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeyom%2Fnot_hotdog_model","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyeyom%2Fnot_hotdog_model","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyeyom%2Fnot_hotdog_model/lists"}