--- title: Rice Classifier ResNet50 emoji: 🌾 colorFrom: green colorTo: yellow sdk: streamlit app_file: src/streamlit_app.py pinned: false short_description: CNN-based rice image classifier with ResNet50. license: mit --- # 🌾 Rice Classification with ResNet50 (Transfer Learning) **Author:** Enes Yamac This app uses a deep learning model to classify rice grain images into different rice types. The model is based on **ResNet50 (Transfer Learning)** and reaches very high accuracy. --- ## πŸš€ What does this app do? This app can: βœ… Classify rice grain images βœ… Detect the rice type automatically βœ… Show the predicted class with confidence βœ… Use a strong AI model trained with transfer learning --- ## 🧠 Model Information - **Model:** ResNet50 (pre-trained on ImageNet) - **Task:** Image Classification - **Number of Classes:** 5 - **Image Size:** 224 Γ— 224 - **Accuracy:** **99.29%** - **Top-3 Accuracy:** **100%** --- ## 🌾 Rice Classes The model can classify the following rice types: - Arborio - Basmati - Ipsala - Jasmine - Karacadag --- ## πŸ–ΌοΈ How to use the app 1. Upload a rice image (JPG or PNG) 2. The model analyzes the image 3. The predicted rice type is shown 4. You also see the confidence score --- ## πŸ“Š Model Performance - Very high accuracy on the validation set - Only a few misclassifications - Most errors happen between visually similar rice types The model is **stable and reliable**. --- ## πŸ§ͺ Training Summary - **Base Model:** ResNet50 - **Transfer Learning:** Yes - **Data Augmentation:** Yes - **Optimizer:** Adam - **Loss Function:** Sparse Categorical Crossentropy - **Batch Size:** 16 --- ## πŸ“ Files in this Space - `app.py` β†’ Streamlit App - `best_rice_resnet50.keras` β†’ Trained Model - `README.md` β†’ This file --- ## πŸ‘€ Author **Name:** Enes Yamac **Date:** 05.12.2025 **Project Type:** Deep Learning – CNN Image Classification with ResNet50 --- βœ… Enjoy testing the rice classifier! Upload an image and let the AI predict the rice type πŸŒΎπŸ€–