Detection in video frame by frame about super-gradients HOT 1 CLOSED

It is fixed! Here is the correct code:

source_folder = "/path/to/videos"
destination_folder = "/path/to/destination/folder"
threshold = 500000
for file in os.listdir(source_folder):
check = False
source_path = os.path.join(source_folder, file)
destination_path = os.path.join(destination_folder, file)
predictions = best_model.predict(source_path, conf=0.8)
# Copy the video file to the destination folder
for frame_prediction in predictions.dict['_images_prediction_gen']:
if len(frame_prediction.prediction.bboxes_xyxy)>0:
for bbox in frame_prediction.prediction.bboxes_xyxy:
Xmin, Ymin, Xmax, Ymax = bbox
Width = Xmax - Xmin
Height = Ymax - Ymin
Area = Width * Height
if Area > threshold:
print(Area)
check = True
if check:
shutil.copyfile(source_path, destination_path)
break

from super-gradients.