Decrease Img number

app.py

@@ -26,9 +26,9 @@ import groundingdino.datasets.transforms as T
 
 from huggingface_hub import hf_hub_download
 
-picture_height = 720
-picture_width = 1080
-picture_fov = 60
+picture_height = 360
+picture_width = 540
+picture_fov = 70
 
 # Use this command for evaluate the GLIP-T model
 config_file = "groundingdino/config/GroundingDINO_SwinT_OGC.py"
@@ -98,21 +98,18 @@ model = load_model_hf(config_file, ckpt_repo_id, ckpt_filenmae)
 def run_grounding(input_image):
     pil_img = Image.fromarray(input_image)
     init_image = pil_img.convert("RGB")
-    original_size = init_image.size
-    grounding_caption = "traffic sign"
+    grounding_caption = "traffic sign, car"
     box_threshold = 0.25
     text_threshold = 0.25
 
     _, 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)
-
-
-    return annotated_frame
+    image_with_box = Image.fromarray(cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB))
+    return image_with_box
 
 
 if __name__ == "__main__":
@@ -128,7 +125,7 @@ if __name__ == "__main__":
         with gr.Row():
             with gr.Column():
                 gallery = gr.Gallery(label="Detection Results").style(
-                    rows=[2],columns=[3], preview=True, object_fit="none")
+                   grid=(1,4), preview=True, object_fit="none")
 
         run_button.click(fn=detection, inputs=[
             input_image], outputs=[gallery])