{"id":28321801,"url":"https://github.com/varunbanka/food-vision","last_synced_at":"2026-04-19T02:06:32.891Z","repository":{"id":252757054,"uuid":"841363845","full_name":"VarunBanka/Food-Vision","owner":"VarunBanka","description":"This project involves the creation of a food vision model using TensorFlow and EfficientNetB0 as the base model. The model is trained on the CIFAR-100 dataset, which contains 100 classes of images.","archived":false,"fork":false,"pushed_at":"2024-08-12T09:14:23.000Z","size":39,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-01T21:13:47.348Z","etag":null,"topics":["ai","computer-vision","data-science","deep-learning","food-vision","machine-learning","tensorflow"],"latest_commit_sha":null,"homepage":"https://github.com/VarunBanka/Food-Vision","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/VarunBanka.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":"2024-08-12T09:02:15.000Z","updated_at":"2025-02-10T01:12:44.000Z","dependencies_parsed_at":"2024-08-12T10:27:06.689Z","dependency_job_id":null,"html_url":"https://github.com/VarunBanka/Food-Vision","commit_stats":null,"previous_names":["varunbanka/food-vision"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/VarunBanka/Food-Vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VarunBanka%2FFood-Vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VarunBanka%2FFood-Vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VarunBanka%2FFood-Vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VarunBanka%2FFood-Vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/VarunBanka","download_url":"https://codeload.github.com/VarunBanka/Food-Vision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VarunBanka%2FFood-Vision/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261220249,"owners_count":23126719,"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":["ai","computer-vision","data-science","deep-learning","food-vision","machine-learning","tensorflow"],"created_at":"2025-05-25T13:09:25.068Z","updated_at":"2026-04-19T02:06:32.814Z","avatar_url":"https://github.com/VarunBanka.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Food Vision Model with TensorFlow\n\nThis project involves the creation of a food vision model using TensorFlow and EfficientNetB0 as the base model. The model is trained on the CIFAR-100 dataset, which contains 100 classes of images.\n\n## Project Overview\n\nThe goal of this project is to build a deep learning model capable of classifying food images into different categories. We used the EfficientNetB0 architecture for feature extraction and performed fine-tuning to improve the model's accuracy.\n\n## Dataset\n\nWe utilized the **CIFAR-100** dataset, which consists of 60,000 32x32 color images in 100 classes, with 600 images per class. There are 50,000 training images and 10,000 test images.\n\n## Model Architecture\n\nThe model is based on the **EfficientNetB0** architecture, a state-of-the-art convolutional neural network model that balances accuracy and computational efficiency. Below is the summary of the model:\n\n| Layer (type)                  | Output Shape       | Param #    |\n| ----------------------------- | ------------------ | ---------- |\n| input_layer (InputLayer)       | (None, 224, 224, 3) | 0          |\n| efficientnetb0 (Functional)    | (None, 7, 7, 1280)  | 4,049,571  |\n| global_avtaging_pooling_2d     | (None, 1280)        | 0          |\n| output_layer (Dense)           | (None, 101)         | 129,381    |\n| softmax_float32 (Activation)   | (None, 101)         | 0          |\n\n- **Total params:** 12,452,816 (47.50 MB)\n- **Trainable params:** 4,136,929 (15.78 MB)\n- **Non-trainable params:** 42,023 (164.16 KB)\n- **Optimizer params:** 8,273,864 (31.56 MB)\n\n## Training Details\n\nThe model was trained for a total of 8 epochs, including 5 epochs of fine-tuning the top layers. Below are the final training metrics:\n\n- **Training Accuracy:** 99.44%\n- **Training Loss:** 0.0293\n- **Validation Accuracy:** 83.33%\n- **Validation Loss:** 0.8154\n\n### Training Process\n\n1. **Initial Training:** The model was initially trained for 3 epochs with the base layers frozen.\n2. **Fine-Tuning:** The top layers of the EfficientNetB0 model were unfrozen, and the entire model was fine-tuned for 5 additional epochs.\n\n### Optimization\n\n- **Optimizer:** Adam\n- **Learning Rate:** Adaptive learning rate with a scheduler.\n- **Loss Function:** Sparse Categorical Crossentropy\n\n## Results\n\nThe model achieved a high training accuracy of 99.44% and a validation accuracy of 83.33% after fine-tuning. Although there is some overfitting indicated by the difference between training and validation accuracy, the model shows promising results for food image classification tasks.\n\n## Running the Project\n\nTo run this project, you can use Google Colab. Here's how to get started:\n\n1. Open Google Colab: [Google Colab](https://colab.research.google.com/)\n2. Upload the notebook (`.ipynb` file) or clone the repository.\n3. Make sure to select a GPU runtime by navigating to `Runtime` \u003e `Change runtime type` and selecting `GPU` under the hardware accelerator.\n4. Run the notebook cells to train and evaluate the model.\n\n## Contributing\n\nIf you'd like to contribute to this project, feel free to fork the repository and submit a pull request. All contributions are welcome!\n\n## License\n\nThis project is licensed under the GNU GENERAL PUBLIC License V3. See the [LICENSE](LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvarunbanka%2Ffood-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvarunbanka%2Ffood-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvarunbanka%2Ffood-vision/lists"}