Added examples

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 this_is_fine.png filter=lfs diff=lfs merge=lfs -text
+demo/Pleiades_HD15_Miami_Marina.jpg filter=lfs diff=lfs merge=lfs -text
+demo/SPOT_Storage.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -3,6 +3,7 @@ from functools import partial
 import cv2
 import requests
 import os
+import time
 from io import BytesIO
 from PIL import Image
 import numpy as np
@@ -27,8 +28,8 @@ import groundingdino.datasets.transforms as T
 from huggingface_hub import hf_hub_download
 
 # check if GPU if available
-#device = torch.device("cuda:0" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu")
-device = 'cpu'
+device = torch.device("cuda:0" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu")
+#device = 'cpu'
 
 # Use this command for evaluate the GLIP-T model
 config_file = "groundingdino/config/GroundingDINO_SwinT_OGC.py"
@@ -74,12 +75,22 @@ def run_grounding(input_image, grounding_caption, box_threshold, text_threshold)
     image_pil: Image = image_transform_grounding_for_vis(init_image)
 
     # run grounidng
+    start_time = time.time()
     boxes, logits, phrases = predict(model, image_tensor, grounding_caption, box_threshold, text_threshold, device=device)
+    end_time = time.time()
     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, str(image_pil.size), len(boxes), end_time - start_time
 
-    return image_with_box
+# Define example images and their true labels for users to choose from
+example_data = [
+    ["./demo/airport01.jpg", "aircraft", 0.25, 0.25]
+    ["./demo/Pleiades_Neo_Tucson_USA.jpg", 0.25, 0.25],
+    ["./demo/SPOT_Storage.jpg", 0.25, 0.25],
+    ["./demo/Satellite_Image_Marina_New_Zealand.jpg", 0.25, 0.25],
+    ["./demo/Pleiades_HD15_Miami_Marina.jpg", 0.25, 0.25],
+]
 
 if __name__ == "__main__":
     
@@ -108,23 +119,20 @@ if __name__ == "__main__":
                 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)
-                    detections = gr.Number(label="Predicted aircrafts", interactive=False)
+                    dimensions = gr.Textbox(label="Image size", interactive=False)
+                    detections = gr.Number(label="Predicted objects", interactive=False)
                     stopwatch = gr.Number(label="Execution time (sec.)", interactive=False, precision=3)
 
             with gr.Column(scale=1):
-                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)
-
-        run_button.click(fn=run_grounding, inputs=[
-                        input_image, grounding_caption, box_threshold, text_threshold], outputs=[gallery])
+                gallery = gr.outputs.Image(type="pil").style(full_width=True, full_height=True)
+
+        run_button.click(fn=run_grounding,
+                        inputs=[input_image, grounding_caption, box_threshold, text_threshold], 
+                        outputs=[gallery, dimensions, detections, stopwatch])
         gr.Examples(
-          [["demo/airport01.jpg", "aircraft", 0.25, 0.25]],
+          examples=example_data,
           inputs = [input_image, grounding_caption, box_threshold, text_threshold],
-          outputs = [gallery],
+          outputs = [gallery, dimensions, detections, stopwatch],
           fn=run_grounding,
           cache_examples=False,
           label='Try this example input!'