You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
During prediction, a warning from Numpy showed only one time:
with sv.VideoSink(target_path=f"{target}.avi", video_info=video_info, codec="H264") as sink:
for image in tqdm(frame_generator, total=video_info.total_frames, unit='frames'):
annotated_image = image.copy()
# Process YOLO-NAS detections
results = list(yolo_nas_model.predict(image, conf=CONFIDENCE, fuse_model=False))[0]
The message is:
C:\anaconda3\envs\vision\lib\site-packages\numpy\lib\arraypad.py:487: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
x = np.array(x)
Versions
Numpy 1.23.0
The text was updated successfully, but these errors were encountered:
I'm sorry for not including more code, sv is for: import supervision as sv. sv.VideoSink is to save a video from the processed frames.
The warning message appears only when executing the first time the line: results = list(yolo_nas_model.predict(image, conf=CONFIDENCE, fuse_model=False))[0]
🐛 Describe the bug
During prediction, a warning from Numpy showed only one time:
The message is:
C:\anaconda3\envs\vision\lib\site-packages\numpy\lib\arraypad.py:487: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
x = np.array(x)
Versions
Numpy 1.23.0
The text was updated successfully, but these errors were encountered: