Update app.py

app.py

@@ -8,7 +8,10 @@ caption_pipeline = pipeline("image-to-text", model="Salesforce/blip-image-captio
 # Initialize the pipeline for emotion classification
 emotion_pipeline = pipeline("image-classification", model="RickyIG/emotion_face_image_classification_v3")
 
-def generate_caption_and_emotion(image):
+# Initialize the pipeline for object detection
+object_pipeline = pipeline("object-detection", model="facebook/detr-resnet-50")
+
+def generate_caption_emotion_and_objects(image):
     # Process the image for captioning
     caption_result = caption_pipeline(image)
     caption = caption_result[0]["generated_text"]
@@ -17,13 +20,16 @@ def generate_caption_and_emotion(image):
     emotion_result = emotion_pipeline(image)
     emotions = ", ".join([f"{res['label']}: {res['score']:.2f}" for res in emotion_result])
 
+    # Process the image for object detection
+    object_result = object_pipeline(image)
+    objects = ", ".join([f"{obj['label']}: {obj['score']:.2f}" for obj in object_result])
+
     # Combine results
-    combined_result = f"Caption: {caption}\nEmotions: {emotions}"
+    combined_result = f"Caption: {caption}\nEmotions: {emotions}\nObjects: {objects}"
     return combined_result
 
 # Setup the Gradio interface
-interface = gr.Interface(fn=generate_caption_and_emotion,
+interface = gr.Interface(fn=generate_caption_emotion_and_objects,
                          inputs=gr.components.Image(type="pil", label="Upload an Image"),
-                         outputs=gr.components.Textbox(label="Generated Caption and Emotions"))
+                         outputs=gr.components.Textbox(label="Generated Caption, Emotions, and Objects Detected"))
 interface.launch()
-