Amey Kulkarni

@XiaoPengZong You might want to experiment with above parameters. Also, I am trying to add more detailed steps and examples with sample video soon in upcoming weeks, if that helps.

> One thing that I kind noticed is that it is better at detecting large faces that are closer to the camera, that's just my initial observation and not too...

@XiaoPengZong Can you add `maintain-aspect-ratio = 1` in [config_infer_primary_masknet_gpu.txt](https://github.com/NVIDIA-AI-IOT/face-mask-detection/blob/master/ds_configs/config_infer_primary_masknet_gpu.txt#L22) ? and try it. Please let me know.

@adrienball I have about 16GB space on my device.

@ClemDoum and @adrienball Any updates on this? I would like to test out on my Jetson board. Please let me know.

Can you check if cam2image is publishing any image by using `ros2 run image_tools cam2image`?

This is supported currently for eloquent. Also, which version on TensorRT are you running? find out using `dpkg -l | grep tensorrt`

I have tested it with `7.1.3.0-1+cuda10.2` on NVIDIA Jetson.