Update app.py

app.py

@@ -28,35 +28,53 @@ def rand_image():
 def set_labels(text):
     return text.split(",")
     
+get_caption = gr.load("ryaalbr/caption", src="spaces")
+def generate_text(image):
+    return get_caption(image)
+    
 with gr.Blocks() as demo:
-    labels = gr.State([])   # creates hidden component that can store a value and can be used as input/output; here, initial value is an empty list
-    instructions = """## Instructions:
-    1. Enter list of labels separated by commas (or select one of the examples below)
-    2. Click **Get Random Image** to grab a random image from dataset and analyze it against the labels
-    3. Click **Re-Classify Image** to re-run classification on current image after changing labels"""
-    gr.Markdown(instructions)
-    with gr.Row(variant="compact"):
-        label_text = gr.Textbox(show_label=False, placeholder="Enter classification labels").style(container=False)
-        #submit_btn = gr.Button("Submit").style(full_width=False)
-    gr.Examples(["spring, summer, fall, winter",
-                 "mountain, city, beach, ocean, desert, forest, valley", 
-                 "red, blue, green, white, black, purple, brown", 
-                 "person, animal, landscape, something else",
-                 "day, night, dawn, dusk"], inputs=label_text)
-    with gr.Row():
-        with gr.Column(variant="panel"):
-            im = gr.Image(interactive=False).style(height=height)
-            with gr.Row():
-                get_btn = gr.Button("Get Random Image").style(full_width=False)
-                reclass_btn = gr.Button("Re-Classify Image").style(full_width=False)
-        cf = gr.Label()
-    #submit_btn.click(fn=set_labels, inputs=label_text)
-    label_text.change(fn=set_labels, inputs=label_text, outputs=labels)  # parse list if changed
-    label_text.blur(fn=set_labels, inputs=label_text, outputs=labels)  # parse list if focus is moved elsewhere; ensures that list is fully parsed before classification
-    label_text.submit(fn=set_labels, inputs=label_text, outputs=labels)  # parse list if user hits enter; ensures that list is fully parsed before classification
-    get_btn.click(fn=rand_image, outputs=im)
-    im.change(predict, inputs=[im, labels], outputs=cf)
-    reclass_btn.click(predict, inputs=[im, labels], outputs=cf)
+
+    with gr.Tab("Zero-Shot Classification"):
+        labels = gr.State([])   # creates hidden component that can store a value and can be used as input/output; here, initial value is an empty list
+        instructions = """## Instructions:
+        1. Enter list of labels separated by commas (or select one of the examples below)
+        2. Click **Get Random Image** to grab a random image from dataset and analyze it against the labels
+        3. Click **Re-Classify Image** to re-run classification on current image after changing labels"""
+        gr.Markdown(instructions)
+        with gr.Row(variant="compact"):
+            label_text = gr.Textbox(show_label=False, placeholder="Enter classification labels").style(container=False)
+            #submit_btn = gr.Button("Submit").style(full_width=False)
+        gr.Examples(["spring, summer, fall, winter",
+                     "mountain, city, beach, ocean, desert, forest, valley", 
+                     "red, blue, green, white, black, purple, brown", 
+                     "person, animal, landscape, something else",
+                     "day, night, dawn, dusk"], inputs=label_text)
+        with gr.Row():
+            with gr.Column(variant="panel"):
+                im = gr.Image(interactive=False).style(height=height)
+                with gr.Row():
+                    get_btn = gr.Button("Get Random Image").style(full_width=False)
+                    reclass_btn = gr.Button("Re-Classify Image").style(full_width=False)
+            cf = gr.Label()
+        #submit_btn.click(fn=set_labels, inputs=label_text)
+        label_text.change(fn=set_labels, inputs=label_text, outputs=labels)  # parse list if changed
+        label_text.blur(fn=set_labels, inputs=label_text, outputs=labels)  # parse list if focus is moved elsewhere; ensures that list is fully parsed before classification
+        label_text.submit(fn=set_labels, inputs=label_text, outputs=labels)  # parse list if user hits enter; ensures that list is fully parsed before classification
+        get_btn.click(fn=rand_image, outputs=im)
+        im.change(predict, inputs=[im, labels], outputs=cf)
+        reclass_btn.click(predict, inputs=[im, labels], outputs=cf)
+
+    with gr.Tab("Image Captioning"):
+        with gr.Row():
+            with gr.Column(variant="panel"):
+                im_cap = gr.Image(interactive=False).style(height=height)
+                with gr.Row():
+                    get_btn_cap = gr.Button("Get Random Image").style(full_width=False)
+                    caption_btn = gr.Button("Create Caption").style(full_width=False)
+            caption = gr.Text()
+        get_btn_cap.click(fn=rand_image, outputs=im_cap)
+        #im_cap.change(generate_text, inputs=im_cap, outputs=caption)
+        caption_btn.click(generate_text, inputs=im_cap, outputs=caption)        
 
 demo.queue()
 demo.launch()