Update app.py

app.py

@@ -78,7 +78,45 @@ def predict2(image_np):
     result_pil_img = tf.keras.utils.array_to_img(image_np_with_detections[0])
     
     return result_pil_img
-
+def write_video(video_in_filepath, video_out_filepath, detection_model):
+    if not os.path.exists(video_in_filepath):
+        print('video filepath not valid')
+    
+    video_reader = cv2.VideoCapture(video_in_filepath)
+    
+    nb_frames = int(video_reader.get(cv2.CAP_PROP_FRAME_COUNT))
+    frame_h = int(video_reader.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    frame_w = int(video_reader.get(cv2.CAP_PROP_FRAME_WIDTH))
+    fps = video_reader.get(cv2.CAP_PROP_FPS)
+    
+    video_writer = cv2.VideoWriter(video_out_filepath,
+                               cv2.VideoWriter_fourcc(*'mp4v'), 
+                               fps, 
+                               (frame_w, frame_h))
+
+    for i in tqdm(range(nb_frames)):
+        ret, image_np = video_reader.read()
+        input_tensor = tf.convert_to_tensor(np.expand_dims(image_np, 0), dtype=tf.uint8)
+        results = detection_model(input_tensor)
+        viz_utils.visualize_boxes_and_labels_on_image_array(
+                  image_np,
+                  results['detection_boxes'][0].numpy(),
+                  (results['detection_classes'][0].numpy()+ label_id_offset).astype(int),
+                  results['detection_scores'][0].numpy(),
+                  category_index,
+                  use_normalized_coordinates=True,
+                  max_boxes_to_draw=200,
+                  min_score_thresh=.50,
+                  agnostic_mode=False,
+                  line_thickness=2)
+
+        video_writer.write(np.uint8(image_np))
+                
+    # Release camera and close windows
+    video_reader.release()
+    video_writer.release() 
+    cv2.destroyAllWindows() 
+    cv2.waitKey(1)
 
 REPO_ID = "YEHTUT/tfodmodel"
 detection_model = load_model()
@@ -90,11 +128,11 @@ detection_model = load_model()
 Image_tab = Interface(fn=predict,
              inputs=gr.Image(type="pil"),
              outputs=gr.Image(type="pil")
-             ).launch(share=True)
+             )
 Video_tab = Interface(fn=predict,
              inputs=gr.Video,
              outputs=gr.Video
-             ).launch(share=True)
+             )
 
 gr.TabbedInterface([Image_tab, Video_tab], ["Image", "Video"]).launch(share=True)
 #gr.Interface(fn=predict,