Translate RGB

app.py

@@ -26,9 +26,9 @@ import groundingdino.datasets.transforms as T
 
 from huggingface_hub import hf_hub_download
 
-picture_height = 360
-picture_width = 540
-picture_fov = 45
+picture_height = 720
+picture_width = 1080
+picture_fov = 60
 
 # Use this command for evaluate the GLIP-T model
 config_file = "groundingdino/config/GroundingDINO_SwinT_OGC.py"
@@ -96,8 +96,7 @@ model = load_model_hf(config_file, ckpt_repo_id, ckpt_filenmae)
 
 
 def run_grounding(input_image):
-    cv2_img_rgb = cv2.cvtColor(input_image, cv2.COLOR_BGR2RGB)
-    pil_img = Image.fromarray(cv2_img_rgb)
+    pil_img = Image.fromarray(input_image)
     init_image = pil_img.convert("RGB")
     original_size = init_image.size
     grounding_caption = "traffic sign"
@@ -111,9 +110,9 @@ def run_grounding(input_image):
     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))
 
-    return image_with_box
+
+    return annotated_frame
 
 
 if __name__ == "__main__":
@@ -126,10 +125,10 @@ if __name__ == "__main__":
             with gr.Column():
                 input_image = gr.Image(source='upload', type="numpy", label="Please upload a panorama picture.")
                 run_button = gr.Button(label="Process & Detect")
-
+        with gr.Row():
             with gr.Column():
                 gallery = gr.Gallery(label="Detection Results").style(
-                    columns=[3], preview=True, object_fit="none")
+                    rows=[2],columns=[3], preview=True, object_fit="none")
 
         run_button.click(fn=detection, inputs=[
             input_image], outputs=[gallery])