YOLOv4 on Jetson Nano using Tensorflow: Internal: too many resources requested for launch

[AastaLLL]

Hi,

As you may know, we have checked this issue several months ago:

Tiny YOLOv4 TensorRT - too many resources requested for launch on 4GB Nano

I’m trying to run a TensorRT Tiny YOLOv4 model on a 4GB Nano development board. I’m running the Nano headless, so should have enough memory (details in jtop output below). And, the model inference definitely works fine on my MacBook CPU. [Screenshot 2020-12-17 at 13.20.40] But, whenever I try to run the inference script on the Nano (available here), I get the following too many resources requested error: 2020-12-16 20:01:04.688877: F tensorflow/core/kernels/resize_bilinear_op_gpu.cu.cc:493]…

The task is terminated since the user found its own solution.
We try to compile a TensorFlow package with maxrregcount = "-maxrregcount=80" but no luck.
( default is maxrregcount = “-maxrregcount=96” )

We will keep checking this and update more information later.

Thanks.