Create app.py

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+from transformers import AutoFeatureExtractor, AutoModelForImageClassification
+
+# Load the feature extractor and model directly
+feature_extractor = AutoFeatureExtractor.from_pretrained("Devarshi/Brain_Tumor_Classification")
+model = AutoModelForImageClassification.from_pretrained("Devarshi/Brain_Tumor_Classification")
+
+# Define the prediction function using the loaded model
+def classify_image(image):
+    # Preprocess the image and obtain features
+    inputs = feature_extractor(images=image, return_tensors="pt")
+    # Make prediction using the model
+    outputs = model(**inputs)
+    logits = outputs.logits
+    # Get the predicted class and confidence of the prediction
+    predicted_class = logits.argmax(dim=1).item()
+    confidence = logits.softmax(dim=1).max().item()
+
+    # Map the predicted class to the correct names
+    class_names = ["glioma_tumor", "meningioma_tumor", "no_tumor", "pituitary_tumor"]
+    predicted_class_text = class_names[predicted_class]
+
+    return {"prediction": predicted_class_text, "confidence": confidence}
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=classify_image,
+    inputs=gr.inputs.Image(),
+    outputs="json",
+    title="Brain Tumor Image Classification",
+    description="This app classifies images of brain tumors into different classes.",
+)
+
+# Launch the Gradio interface
+if __name__ == "__main__":
+    iface.launch()