{"id":22514073,"url":"https://github.com/omraj0/food-vision","last_synced_at":"2026-04-18T06:31:50.747Z","repository":{"id":247715658,"uuid":"826653627","full_name":"omraj0/Food-Vision","owner":"omraj0","description":"A deep learning model using CNN to classify food images into various recipe categories with high accuracy. ","archived":false,"fork":false,"pushed_at":"2025-01-29T18:03:49.000Z","size":4607,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T01:44:38.856Z","etag":null,"topics":["efficientnetv2","google-colab","keras","python","resnet-50","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/omraj0.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":"2024-07-10T05:57:46.000Z","updated_at":"2025-01-29T18:05:38.000Z","dependencies_parsed_at":"2025-01-29T19:31:27.732Z","dependency_job_id":null,"html_url":"https://github.com/omraj0/Food-Vision","commit_stats":null,"previous_names":["omraj0/food-vision"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/omraj0/Food-Vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omraj0%2FFood-Vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omraj0%2FFood-Vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omraj0%2FFood-Vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omraj0%2FFood-Vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/omraj0","download_url":"https://codeload.github.com/omraj0/Food-Vision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omraj0%2FFood-Vision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31959873,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T00:39:45.007Z","status":"online","status_checked_at":"2026-04-18T02:00:07.018Z","response_time":103,"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":["efficientnetv2","google-colab","keras","python","resnet-50","tensorflow"],"created_at":"2024-12-07T03:15:47.524Z","updated_at":"2026-04-18T06:31:50.726Z","avatar_url":"https://github.com/omraj0.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🍲 Food Vision (Food Image Classification)\n\nThis project demonstrates an image classification application using TensorFlow and Streamlit. The model is trained to classify images of various Indian food items.\n\n## 📋 Table of Contents\n- [📦 Installation](#-installation)\n- [🚀 Usage](#-usage)\n- [🔍 Model Training](#-model-training)\n  - [ResNet50](#resnet50)\n  - [EfficientNet](#efficientnet)\n- [🤖 Model Prediction](#-model-prediction)\n- [📁 Project Structure](#-project-structure)\n- [🙏 Acknowledgements](#-acknowledgements)\n\n## 📦 Installation\n### Clone the repository:\n   ```bash\n   git clone https://github.com/omraj0/food-vision.git\n   cd food-vision\n  ```\n**Install the required packages:**\n```bash\npip install -r requirements.txt\n```\n## 🚀 Usage\nTo run the Streamlit app locally, use the following command:\n```bash\nstreamlit run app.py\n```\n## 🔍 Model Training\n\nThe model is based on two popular architectures: ResNet50 and EfficientNetV2B0, both of which are trained on a dataset of Indian food images.\n\n### ResNet50\n\nResNet50 is a deep residual network that helps to mitigate the vanishing gradient problem by using residual blocks. This model is highly effective for image classification tasks and has been pre-trained on the ImageNet dataset.\n\n### EfficientNet\n\nEfficientNetV2B0 is a family of models that efficiently scale up the size of the network. It balances network depth, width, and resolution to achieve better performance with fewer parameters.\n\n### Training Process\n\n- **Data Preparation**: The images are loaded and preprocessed using TensorFlow's `tf.keras.preprocessing.image_dataset_from_directory` method.\n- **Model Architecture**: The model uses either ResNet50 or EfficientNetV2B0 as the base model with a custom top layer for classification into 80 classes.\n- **Training**: The model is trained with data augmentation to improve its generalization capability. The training script can be found in the `train.py` file.\n\n## 🤖 Model Prediction\n\nThe prediction script (`img_classification.py`) loads a trained model and makes predictions on new images. The `load_and_prep_image` function preprocesses the image, and the `predict_data` function makes the prediction and returns the predicted class.\n\n## 📁 Project Structure\n\n```bash\n.\n├── app.py                      # Streamlit app script\n├── img_classification.py       # Image classification script\n├── train.py                    # Model training script\n├── requirements.txt            # Python packages required\n└── README.md                   # Project README file\n```\n## 🙏 Acknowledgements\nThis project is inspired by the Food-101 dataset and uses the ResNet50 and EfficientNetV2B0 models from TensorFlow.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomraj0%2Ffood-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fomraj0%2Ffood-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomraj0%2Ffood-vision/lists"}