Update app.py

app.py

@@ -1,3 +1,30 @@
 import gradio as gr
+from transformers import CLIPProcessor, CLIPModel
+from PIL import Image
+import requests
 
-gr.load("models/geolocal/StreetCLIP").launch()
+# Load the model and processor
+model = CLIPModel.from_pretrained("geolocal/StreetCLIP")
+processor = CLIPProcessor.from_pretrained("geolocal/StreetCLIP")
+
+def classify_image(image):
+    # Preprocess the image
+    inputs = processor(images=image, return_tensors="pt")
+    # Perform the inference
+    outputs = model(**inputs)
+    # Postprocess the outputs
+    logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
+    probs = logits_per_image.softmax(dim=1)  # we can use softmax to get probabilities
+    return probs
+
+# Define Gradio interface
+iface = gr.Interface(
+    fn=classify_image,
+    inputs=gr.inputs.Image(type="pil"),
+    outputs="text",
+    title="Geolocal StreetCLIP Classification",
+    description="Upload an image to classify using Geolocal StreetCLIP"
+)
+
+# Launch the interface
+iface.launch()