file display

main.py

@@ -26,6 +26,7 @@ human3d = MMPoseInferencer(pose3d="human3d")
 # Defining inferencer models to lookup in function
 inferencers = {"Estimate human 2d poses":human, "Estimate human 2d hand poses":hand, "Estimate human 3d poses":human3d}
 
+#track_model = YOLO('yolov8n.pt')  # Load an official Detect model
 
 print("[INFO]: Downloaded models!")
 
@@ -37,9 +38,42 @@ def tracking(video, model, boxes=True):
     print("[INFO] Starting tracking!")
     # https://docs.ultralytics.com/modes/predict/
     annotated_frame = model(video, device="cuda", boxes=boxes)
-    
+
     return annotated_frame
 
+
+
+#def show_tracking(video_content):
+
+        video = cv2.VideoCapture(video_content)
+
+        # Track
+        video_track = tracking(video_content, track_model.track)
+
+        # Prepare to save video
+        output_file_track = os.path.join("track.mp4")
+
+        fourcc = cv2.VideoWriter_fourcc(*"mp4v")  # Codec for MP4 video
+        fps = video.get(cv2.CAP_PROP_FPS)
+        height, width, _ = video_track[0][0].orig_img.shape
+        size = (width,height)
+
+        out_track = cv2.VideoWriter(output_file_track, fourcc, fps, size)
+
+        # Go through frames and write them 
+        for frame_track in video_track:
+            result_track = frame_track[0].plot()  # plot a BGR numpy array of predictions
+
+        #print(type(result_pose)) numpy ndarray
+        out_track.write(result_track)
+
+        out_track.release()
+
+        video.release()
+        cv2.destroyAllWindows() # Closing window
+
+        return output_file_track
+
 def poses(photo, check):
     # Selecting the specific inferencer
     out_files=[]
@@ -73,7 +107,7 @@ def run():
     webcam = gr.Interface(
         fn=poses,
         inputs= [gr.Video(source="webcam", height=412), check_web],
-        outputs = [gr.PlayableVideo()]*len(["Estimate human 2d poses", "Estimate human 2d hand poses", "Estimate human 3d poses"]),  #file_types=['.mp4'] #gr.Video(),
+        outputs = [gr.PlayableVideo(),gr.PlayableVideo(),gr.PlayableVideo()],  #file_types=['.mp4'] #gr.Video(),
         title = 'Pose estimation', 
         description = 'Pose estimation on video',
         allow_flagging=False
@@ -82,7 +116,7 @@ def run():
     file = gr.Interface(
         poses,
         inputs = [gr.Video(source="upload", height=412), check_file],
-        outputs = [gr.PlayableVideo()]*len(["Estimate human 2d poses", "Estimate human 2d hand poses", "Estimate human 3d poses"]),
+        outputs = [gr.PlayableVideo(),gr.PlayableVideo(),gr.PlayableVideo()],
         allow_flagging=False
     )