Update app.py

app.py

@@ -19,31 +19,37 @@ construction_terms = [
 ]
 
 # Inference function
-def generate_caption(image):
-    if image.mode != "RGB":
-        image = image.convert("RGB")
+def generate_captions(images):
+    captions = []
     
-    # Preprocess the image and generate a caption
-    inputs = processor(image, return_tensors="pt").to(device, torch.float16)
-    output = model.generate(**inputs, max_new_tokens=50)
-    caption = processor.decode(output[0], skip_special_tokens=True)
+    for image in images:
+        if image.mode != "RGB":
+            image = image.convert("RGB")
+        
+        # Preprocess the image and generate a caption
+        inputs = processor(image, return_tensors="pt").to(device, torch.float16)
+        output = model.generate(**inputs, max_new_tokens=50)
+        caption = processor.decode(output[0], skip_special_tokens=True)
 
-    # Filter the caption to only include construction-related terms
-    filtered_caption = " ".join([word for word in caption.split() if word.lower() in construction_terms])
+        # Filter the caption to only include construction-related terms
+        filtered_caption = " ".join([word for word in caption.split() if word.lower() in construction_terms])
+        
+        # If no construction-related terms are found, return a default message
+        if not filtered_caption:
+            filtered_caption = "No construction-related activities detected."
+        
+        captions.append(filtered_caption)
     
-    # If no construction-related terms are found, return a default message
-    if not filtered_caption:
-        filtered_caption = "No construction-related activities detected."
-    
-    return filtered_caption
+    return captions
 
 # Gradio interface
 iface = gr.Interface(
-    fn=generate_caption,
-    inputs=gr.Image(type="pil"),
+    fn=generate_captions,
+    inputs=gr.Image(type="pil", tool="editor", label="Upload Site Photos", multiple=True),
     outputs="text",
     title="Construction Site Image-to-Text Generator",
-    description="Upload a site photo. The model will detect and describe construction activities and materials (e.g., concrete pouring, scaffolding, steel rods)."
+    description="Upload up to 10 site photos. The model will detect and describe construction activities and materials (e.g., concrete pouring, scaffolding, steel rods).",
+    allow_flagging="never"
 )
 
 iface.launch()