kikuyu-resnet50-onnx

Kikuyu ResNet50 Fine-tuned Model

This model is a fine-tuned ResNet50 image classification model trained on Kikuyu cultural images (e.g., initiation, ceremonies, and traditional wear).

🧠 Model Details

• Base Model: ResNet50 (ImageNet pre-trained)
• Framework: TensorFlow → converted to ONNX
• Input size: 224x224 RGB
• Output: Probability distribution over cultural categories

🚀 How to Use

You can use this model with the Hugging Face Inference API:

from huggingface_hub import InferenceClient

client = InferenceClient("Pruddie/kikuyu-resnet50-onnx")
image_path = "sample.jpg"

with open(image_path, "rb") as f:
    result = client.post("/predict", files={"image": f})

print(result.json())