ui

app.py

@@ -114,19 +114,6 @@ def merge_nearby_rectangles(rectangles, nearness):
 
 def run_detection(input_image):
 
-    """"
-    init_image = input_image.convert("RGB")
-    original_size = init_image.size
-
-    _, image_tensor = image_transform_grounding(init_image)
-    image_pil: Image = image_transform_grounding_for_vis(init_image)
-
-    # run grounidng
-    boxes, logits, phrases = predict(model, image_tensor, grounding_caption, box_threshold, text_threshold, device='cpu')
-    annotated_frame = annotate(image_source=np.asarray(image_pil), boxes=boxes, logits=logits, phrases=phrases)
-    image_with_box = Image.fromarray(cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB))
-    """
-
     # inputimage is PIL as RGB
     image = np.asarray(input_image.convert("RGB"))
 
@@ -160,32 +147,21 @@ if __name__ == "__main__":
         with gr.Row():
             with gr.Column():
                 input_image = gr.Image(source='upload', type="pil")
-                grounding_caption = gr.Textbox(label="Detection Prompt")
                 run_button = gr.Button(label="Run")
-                with gr.Accordion("Advanced options", open=False):
-                    box_threshold = gr.Slider(
-                        label="Box Threshold", minimum=0.0, maximum=1.0, value=0.25, step=0.001
-                    )
-                    text_threshold = gr.Slider(
-                        label="Text Threshold", minimum=0.0, maximum=1.0, value=0.25, step=0.001
-                    )
+                info = gr.Textbox(label="Info")
+                
 
             with gr.Column():
-                gallery = gr.outputs.Image(
-                    type="pil",
-                    # label="grounding results"
-                ).style(full_width=True, full_height=True)
-                # gallery = gr.Gallery(label="Generated images", show_label=False).style(
-                #         grid=[1], height="auto", container=True, full_width=True, full_height=True)
+                gallery = gr.outputs.Image(type="pil").style(full_width=True, full_height=True)
 
         run_button.click(fn=run_detection, inputs=[
                         input_image], outputs=[gallery])
         gr.Examples(
-          [["Sample1.jpg", "coffee cup"],["Sample2.jpg", "coffee cup"]],
+          [["Sample1.jpg"],["Sample2.jpg"]],
           inputs = [input_image],
           outputs = [gallery],
           fn=run_detection,
           cache_examples=True,
-          label='Try this example input!'
+          label='Try these examples:'
       )
     block.launch(share=False, show_api=False, show_error=True)