Spaces:
Sleeping
Sleeping
|
Download README.md from EnYa32/Rice-Classifier-CNN: direct link, hf CLI and curl.
- Browser
- Download file 2.25 kB
-
https://huggingface.co/spaces/EnYa32/Rice-Classifier-CNN/resolve/main/README.md
- Command line
-
hf download hf://spaces/EnYa32/Rice-Classifier-CNN/README.md
-
curl -L -o README.md https://huggingface.co/spaces/EnYa32/Rice-Classifier-CNN/resolve/main/README.md
2.25 kB
| title: Rice Classification CNN | |
| emoji: πΎ | |
| colorFrom: green | |
| colorTo: yellow | |
| sdk: streamlit | |
| app_file: src/streamlit_app.py | |
| pinned: false | |
| short_description: Rice image classifier CNN. | |
| license: mit | |
| # Rice Classification using CNN (From Scratch) | |
| This project implements a **Convolutional Neural Network (CNN) from scratch** to classify rice grain images into five different types: | |
| - Arborio | |
| - Basmati | |
| - Ipsala | |
| - Jasmine | |
| - Karacadag | |
| The model was trained without transfer learning and achieves **very high accuracy** on the validation dataset. | |
| --- | |
| ## π Dataset | |
| - Total images: **75,000** | |
| - Classes: **5** | |
| - Train / Validation Split: **80% / 20%** | |
| - Image size: **160 Γ 160** | |
| - Batch size: **16** | |
| - Background: Black (single rice grain per image) | |
| --- | |
| ## π§ Model Overview | |
| The CNN architecture includes: | |
| - 5 Convolutional Layers | |
| - 3 MaxPooling Layers | |
| - Batch Normalization | |
| - L2 Regularization | |
| - Data Augmentation (Flip, Rotation, Zoom) | |
| - Global Average Pooling | |
| - Dense Layer with Dropout | |
| - Softmax Output Layer (5 classes) | |
| --- | |
| ## βοΈ Training Setup | |
| - Loss Function: **Sparse Categorical Crossentropy** | |
| - Optimizer: **Adam (learning rate = 0.0001)** | |
| - Metrics: **Accuracy** | |
| - Epochs: **40** | |
| - Callbacks: | |
| - EarlyStopping | |
| - ReduceLROnPlateau | |
| - ModelCheckpoint | |
| --- | |
| ## π Results | |
| - β **Validation Accuracy:** **99.94%** | |
| - β **Validation Loss:** **0.0179** | |
| - β **Precision, Recall, F1-Score:** **1.00 for all classes** | |
| - β **Only 9 misclassifications out of 75,000 images** | |
| The confusion matrix shows nearly perfect classification performance. | |
| --- | |
| ## π Future Work | |
| - Test the model on real-world images | |
| - Apply stronger data augmentation | |
| - Compare with a **Transfer Learning model (e.g. ResNet50)** | |
| - Deploy as a **Streamlit Web App** | |
| --- | |
| ## π€ Author | |
| **Name:** Enes Yamac | |
| **Date:** 05.12.2025 | |
| **Project Type:** Deep Learning β CNN Image Classification | |
| --- | |
| ## π Files in this Project | |
| - `best_rice_cnn.keras` β Trained CNN model | |
| - `rice_cnn_training.ipynb` β Jupyter Notebook (training & evaluation) | |
| - `Rice_CNN_Report_Enes_Yamac.pdf` β Technical Report | |
| - `README.md` β Project description | |
| --- | |
| β **Status:** Project completed successfully. |