Create app.py

app.py

@@ -0,0 +1,53 @@
+import tensorflow as tf
+from PIL import Image
+import numpy as np
+import gradio as gr
+from huggingface_hub import hf_hub_download
+
+# Load the trained model
+repo_id = "methestrikerx100/Mineral_Identifcation_Project"
+filename = "Deployment.h5"
+
+# Download the model file
+model_path = hf_hub_download(repo_id=repo_id, filename=filename)
+
+# Load the model
+model = tf.keras.models.load_model(model_path)
+
+# Define the class labels
+class_labels = ['biotite', 'granite', 'olivine', 'plagioclase', 'staurolite']
+
+# Define the function to make predictions
+def classify_image(image):
+    # Preprocess the image
+    image = np.array(image)
+    image = Image.fromarray(image.astype(np.uint8), 'RGB')
+    image = image.resize((224, 224))
+    image = np.array(image) / 255.0
+    image = np.expand_dims(image, axis=0)
+
+    # Make prediction
+    prediction = model.predict(image)
+    class_idx = np.argmax(prediction)
+    prediction_scores = prediction[0]
+
+    # Convert prediction scores to percentages
+    prediction_scores_percentages = [f"{score * 100:.2f}%" for score in prediction_scores]
+
+    # Create formatted output strings
+    predicted_class_name = class_labels[class_idx]
+    predicted_scores = "\n".join([f"{label}: {score}" for label, score in zip(class_labels, prediction_scores_percentages)])
+
+    return predicted_class_name, predicted_scores
+
+# Create the Gradio interface
+with gr.Blocks() as demo:
+    with gr.Row():
+        image_input = gr.Image(elem_id="image_input", type="pil")
+        output_components = [
+            gr.Textbox(elem_id="predicted_class_name"),
+            gr.Textbox(elem_id="predicted_scores", lines=5)
+        ]
+        image_button = gr.Button("Classify Image")
+        image_button.click(classify_image, inputs=image_input, outputs=output_components)
+demo.launch(share=True)