KEDU Breed Classifier (swin_tiny_patch4_window7_224)

How to Use

1. Install dependencies:
   pip install torch torchvision timm pytorch-lightning albumentations opencv-python-headless scikit-learn Pillow huggingface_hub python-box PyYAML
2. Download inference.py, pytorch_model.ckpt, and label_encoder.pkl from this repository.
3. Run inference:
   python

   1from inference import load_model_from_hf, load_label_encoder_from_hf, predict_breed 2 3model = load_model_from_hf(repo_id="Hajorda/keduClassifier") 4label_encoder = load_label_encoder_from_hf(repo_id="Hajorda/keduClassifier") 5 6image_path = "path/to/your/pet_image.jpg" # Replace with your image path 7predicted_breed, confidence = predict_breed(image_path, model, label_encoder) 8print(f"Predicted: {predicted_breed}, Confidence: {confidence:.4f}")

Model Details

• Dataset: Oxford-IIIT Pet Dataset
• Number of Classes: 37
• Image Size: (224, 224)

Performance

• Validation Accuracy: 93.40% (Note: This is the validation accuracy from the training run.)

Author