Update app.py

app.py

@@ -5,14 +5,25 @@ from PIL import Image
 # Initialize the pipeline with the image captioning model
 caption_pipeline = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
 
-def generate_caption(image):
-    # The image is received as a PIL Image, so no need for conversion
-    result = caption_pipeline(image)
-    caption = result[0]["generated_text"]
-    return caption
+# Initialize the pipeline for emotion classification
+emotion_pipeline = pipeline("image-classification", model="RickyIG/emotion_face_image_classification_v3")
+
+def generate_caption_and_emotion(image):
+    # Process the image for captioning
+    caption_result = caption_pipeline(image)
+    caption = caption_result[0]["generated_text"]
+
+    # Process the image for emotion classification
+    emotion_result = emotion_pipeline(image)
+    emotions = ", ".join([f"{res['label']}: {res['score']:.2f}" for res in emotion_result])
+
+    # Combine results
+    combined_result = f"Caption: {caption}\nEmotions: {emotions}"
+    return combined_result
 
 # Setup the Gradio interface
-interface = gr.Interface(fn=generate_caption,
+interface = gr.Interface(fn=generate_caption_and_emotion,
                          inputs=gr.components.Image(type="pil", label="Upload an Image"),
-                         outputs=gr.components.Textbox(label="Generated Caption"))
+                         outputs=gr.components.Textbox(label="Generated Caption and Emotions"))
 interface.launch()
+