Upload 2 files

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+import tensorflow as tf
+from tensorflow.keras.preprocessing import image
+import numpy as np
+from PIL import Image
+from keras import layers
+
+# Load your trained Xception model
+model = tf.keras.models.load_model("xception-head")
+
+# Define the labels for your classification
+class_labels = ['fresh', 'early decay', 'advanced decay','skeletonized']  # Replace with your actual class names
+
+def classify_image(img):
+    # Preprocess the image to fit the model input shape
+    img = img.resize((299, 299))  # Xception takes 299x299 input size
+    img = np.array(img) / 255.0   # Normalize the image
+    img = np.expand_dims(img, axis=0)
+
+    # Make prediction
+    predictions = model.predict(img)
+    predicted_class = np.argmax(predictions, axis=1)[0]
+    confidence = np.max(predictions)
+    return {class_labels[i]: float(predictions[0][i]) for i in range(len(class_labels))}, confidence
+
+# Example images (local paths or URLs)
+#example_images = [
+    #'examples/fresh.jpg',  # Replace with actual local file paths or URLs
+#]
+
+# Gradio interface
+demo = gr.Interface(
+    fn=classify_image,
+    title="Human Decomposition Image Classification",
+    description = "Predict the stage of decay (fresh, early decay, advanced decay, or skeletonized) of a head. This is a demo of one of our human decomposition image classification <a href=\"https://huggingface.co/icputrd/megyesi_decomposition_classification/blob/main/head/xception\">models</a>.",
+    inputs=gr.Image(type="pil"),
+    outputs=[gr.Label(num_top_classes=len(class_labels)), gr.Number()],
+    live=True,
+    article = "Author: <a href=\"https://www.linkedin.com/in/anna-maria-nau/\">Anna-Maria Nau</a>"
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+pillow
+transformers
+tensorflow==2.11.0
+keras==2.11.0
+numpy==1.24.4