ReddyTintaya

use docker "docker push alantrrs/cuda-opencv:latest"

compiling opencv for using it with the GPU is a headache and installing CUDA for and CUDNN too, it isn't easy, but if you use docker it has inside already...

@rEufrazio .

you say that you're passing your bounding boxes from another detector right? is that detector using the gpu? can you share the lines of how you're passing your bounding boxes?

It says Core Dumped it means that you are out of memory in your gpu try executing in the command line ``` nvidia-smi ``` it will give you the usage...

in the 135 line change this `_, contours, hierarchy = cv2.findContours(work, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)` to this `contours, hierarchy = cv2.findContours(work, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)` it's because in a previous version of opencv that...

i use a video capture Async method and works really well in a 1050ti and even better in a 2080ti

https://github.com/Reddyforcode/thermal_camera_mtcnn/blob/master/videocaptureasync.py remove from the 9th line to 17th line for just the source that you want to have ```self.src=0 ``` for your local webcam use: ```` from videocaptureasync import VideoCaptureAsync...

> ```python > groups = [ > CombinedGroup(filters=['first_name', 'last_name'], combine=operator.or_), > ] > ``` @mohsnMohsni That is tied to his PR, is not part of django_filters

Just FYI, GitHub allows you to upload images 😅 It would be helpful if you share also some code to see what may be happening here.