Upload app.py

app.py

@@ -5,7 +5,6 @@ from tensorflow.keras.preprocessing import image
 from huggingface_hub import snapshot_download
 import os
 
-
 # Load the model from Hugging Face Hub
 def load_model(repo_id):
     download_dir = snapshot_download(repo_id)
@@ -13,7 +12,6 @@ def load_model(repo_id):
     model = tf.keras.models.load_model(model_path)
     return model
 
-
 # Function to preprocess the uploaded image
 def preprocess_image(img, target_size=(224, 224)):
     img = img.resize(target_size)  # Resize to match model input
@@ -22,7 +20,6 @@ def preprocess_image(img, target_size=(224, 224)):
     img_array = tf.keras.applications.efficientnet.preprocess_input(img_array)
     return img_array
 
-
 # Perform inference
 def predict(image_input):
     class_names = ["Defective Tyre", "Good Tyre"]
@@ -37,9 +34,8 @@ def predict(image_input):
 
     return f"Predicted Class: {predicted_class} (Confidence: {prediction:.5f})"
 
-
 # Hugging Face Model Repository ID
-REPO_ID = "skngew/9053220B"  # Change this to your actual repo ID
+REPO_ID = "your-huggingface-repo-id"  # Change this to your actual repo ID
 
 # Load the model
 model = load_model(REPO_ID)
@@ -47,6 +43,13 @@ model = load_model(REPO_ID)
 # Student ID
 student_id = "Student ID: 9053220B"
 
+# Markdown description to show classification threshold
+threshold_info = """
+### Classification Threshold:
+- A tyre is classified as **Good** if the confidence score is **≥ 0.5**.
+- A tyre is classified as **Defective** if the confidence score is **< 0.5**.
+"""
+
 # Create the Gradio interface
 interface = gr.Interface(
     fn=predict,
@@ -54,7 +57,15 @@ interface = gr.Interface(
     outputs=gr.Textbox(label="Prediction"),
     title="Binary Classification: Good vs. Defective Tire",
     description=student_id,
+    allow_flagging="never",
+    examples=[],  # You can add example images here if needed
 )
 
+# Add the threshold information markdown
+with gr.Blocks() as app:
+    gr.Markdown(threshold_info)  # Display threshold info
+    interface.render()
+
 # Launch the Gradio app
-interface.launch(share=True)
+app.launch(share=True)
+