Crashes after the 1st few frames about refacer HOT 5 CLOSED

While we identify and resolve the issue, you can also use the CPU mode with the —force_cpu flag.

Use this command:

python app.py —force_cpu

from refacer.

Video size: 640x352

src image size: 512x583
dst image size: 512x512

TENSORRT mode with providers ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider']

from refacer.

With CUDAExecutionProvider it works!

from refacer.

Thank you for reporting this issue. In order to better diagnose the problem, could you please provide more information? Specifically, could you share the size of the video you're trying to process and the size of the images you've uploaded as faces?Also, could you please specify which ProcessExecutor the program is picking up? Is it TensorrtExecutionProvider or CUDAExecutionProvider?

I apologize for the inconvenience, I'm aware that the error handling and messaging need improvements. Your feedback is extremely valuable in this regard.

I want to add that initially, my focus was on functionality. I have recently been working on performance enhancements. Now, I'm about to shift my focus to better error handling. While I work on identifying and resolving this issue, I would suggest trying out the application on Google Colab, if possible. This might offer a temporary workaround. Thank you for your understanding and patience.

from refacer.

While we have not yet resolved the bug, we have disabled TensorrtExecutionProvider. It should now automatically use CUDAExecutionProvider and should work for you. Could you let us know if this is the case? At the moment we don't have an NVIDIA GPU to test on

from refacer.