|
Download README.md from EnYa32/Date-Fruit-Classification-ResNet50: direct link, hf CLI and curl.
- Browser
- Download file 2.93 kB
-
https://huggingface.co/spaces/EnYa32/Date-Fruit-Classification-ResNet50/resolve/main/README.md
- Command line
-
hf download hf://spaces/EnYa32/Date-Fruit-Classification-ResNet50/README.md
-
curl -L -o README.md https://huggingface.co/spaces/EnYa32/Date-Fruit-Classification-ResNet50/resolve/main/README.md
2.93 kB
| title: DateFruitClassifierResNet50 | |
| emoji: π΄ | |
| colorFrom: gray | |
| colorTo: green | |
| sdk: streamlit | |
| app_file: src/streamlit_app.py | |
| pinned: false | |
| short_description: Date fruit image classifier app using ResNet50. | |
| license: mit | |
| # π¦ Date Fruit Classification using ResNet50 (Transfer Learning) | |
| ## π Project Summary | |
| This project classifies different types of date fruits using deep learning. | |
| Because the dataset is small and the fruits look very similar, I used **Transfer Learning with ResNet50**, a model pre-trained on ImageNet. This helped improve accuracy and reduce training time. | |
| --- | |
| ## π― Goals | |
| - Classify multiple date fruit types using images | |
| - Use ResNet50 with transfer learning | |
| - Compare model results with a CNN trained from scratch | |
| - Evaluate with accuracy/loss curves and classification report | |
| - Write a technical report (included as PDF) | |
| --- | |
| ## π Results | |
| | Model | Validation Accuracy | Validation Loss | Macro F1-score | | |
| |-------|---------------------|-----------------|----------------| | |
| | Custom CNN (no TL) | ~90% | ~0.30 | ~0.88 | | |
| | **ResNet50 (with TL)** | **94.22%** | **0.1842** | **0.94** | | |
| β Transfer Learning improved accuracy | |
| β Model did not overfit | |
| β Works well at classifying most types | |
| --- | |
| ## π§ Model Used | |
| ResNet50 (ImageNet weights, frozen) | |
| β GlobalAveragePooling2D | |
| β Dense(256, relu) | |
| β Dropout(0.5) | |
| β Dense(num_classes, softmax) | |
| yaml | |
| Code kopieren | |
| --- | |
| ## π§ Training Settings | |
| | Option | Value | | |
| |--------|-------| | |
| | Optimizer | Adam (lr = 0.001) | | |
| | Loss | sparse_categorical_crossentropy | | |
| | Batch Size | 16 | | |
| | Epochs | 40 | | |
| | Validation Split | 20% | | |
| | Callbacks | ReduceLROnPlateau, ModelCheckpoint, EarlyStopping | | |
| --- | |
| ## π Files | |
| π project_folder | |
| β | |
| βββ app.py # Optional Streamlit app | |
| βββ model_resnet50.keras # Trained model | |
| βββ notebook.ipynb # Training notebook | |
| βββ history_resnet50.pkl # Training history | |
| βββ resnet50_transfer_learning_report.pdf # Full report (EN + DE) | |
| βββ README.md # This file | |
| yaml | |
| Code kopieren | |
| --- | |
| ## π How to Use the Model | |
| ```python | |
| from tensorflow.keras.models import load_model | |
| import numpy as np | |
| from tensorflow.keras.preprocessing import image | |
| model = load_model('model_resnet50.keras') | |
| img = image.load_img('test_image.jpg', target_size=(224, 224)) | |
| img_array = image.img_to_array(img) | |
| img_array = np.expand_dims(img_array, axis=0) | |
| prediction = model.predict(img_array) | |
| print(prediction) | |
| π Next Steps (Optional) | |
| Fine-tune ResNet50 (unfreeze some layers, lower learning rate) | |
| Add more images to improve weak classes | |
| Try class weighting | |
| π **Download Technical Report (PDF)** | |
| [CNN_Date_Report.pdf](./resnet50_report.pdf) | |
| π§βπ» Author | |
| Enes Yamac | |
| Deep Learning Project β Transfer Learning with ResNet50 | |
| π November 2025 | |
| π Final Note | |
| Transfer Learning helped achieve high accuracy and reliable classification performance. |