Thomas Merlet

icon indicating a website link http://thomas-merlet.github.io/ icon indicating an email [email protected]

icon company ENSAM / CentraleSupélec icon location Paris, France icon location Computer Science and Robotics Engineer from CentraleSupélec and Arts et Métiers French Engineering schools.

Results 4 comments of Thomas Merlet

Unable to use YOLOv3 model

Hi Giovanni, Yes, might be a similar issue. I think [this issue ](https://github.com/intel/ros_openvino_toolkit/issues/32) is related as well. YOLOv3 has 3 output layers which is not the current network output size.

Unable to use YOLOv3 model

Hi @ajtudela, the best way would be indeed to create a new detection node for YOLOv3, unfortunately I had no time to look at it yet.

Unable to use YOLOv3 model

Hi @gbr1 , about this, do you have a way to make sure it runs on NCS2? I don't see much difference in performance when changing the target, ant the...

Lanching with multiple camera_nodelet_manager gives erratic behavior

@MathiasStokholm Yes, I've actually encountered this problem on multiple computer, with different installation. I was using Spinnaker SDK 2.5.0.80 for my tests.