Upload 3 files

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+
+# ---------- Load your trained model ----------
+model = tf.keras.models.load_model("final_model.h5")
+
+# ---------- Prediction function ----------
+def predict(image):
+    # Resize the input image to the size your model expects (update if different)
+    img = image.resize((224, 224))  # change size if your model was trained differently
+    img_array = np.array(img) / 255.0  # normalize
+    
+    # Expand dimensions for batch
+    img_array = np.expand_dims(img_array, axis=0)
+    
+    # Predict
+    prediction = model.predict(img_array)[0][0]  # assumes binary classification
+    
+    # Convert probability to label
+    if prediction > 0.5:
+        result = f"🟥 Malignant (Cancer Detected) with {prediction*100:.2f}% confidence"
+    else:
+        result = f"🟩 Benign (No Cancer) with {(1-prediction)*100:.2f}% confidence"
+    
+    return result
+
+# ---------- Define Gradio UI ----------
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil", label="Upload Skin Lesion Image"),
+    outputs=gr.Textbox(label="Prediction"),
+    title="🧬 Skin Cancer Detection",
+    description="Upload a skin lesion image and the model will predict whether it is Benign or Malignant."
+)
+
+# ---------- Launch ----------
+if __name__ == "__main__":
+    demo.launch()

final_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff8ac00211462b4b533154bae22362e5501838219a1dfb9eecf3bd8121ca533
+size 24526712

requirements.txt

@@ -0,0 +1,4 @@
+tensorflow
+opencv-python
+numpy
+gradio