1

I succesfull converted the .weight file to .tf file, then i used the convert_trt.py scirpt which indeed is getting killed after a 2 mins wait.

I use a Jetson Xavier nx, Cuda 10.2.

Error log:

..
..
.
2020-08-22 15:31:22.362558: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3624 MB memory) -> physical GPU (device: 0, name: Xavier, pci bus id: 0000:00:00.0, compute capability: 7.2)
Killed
Sai Krishnadas
  • 2,863
  • 9
  • 36
  • 69
  • 1
    I've got this problem as well. It appears to be the Out Of Memory killer that kills it. But I don't know why it gets OOM when converting a model that's only a couple of hundred MB on a system with ~5GB RAM free to start with. – IBBoard Nov 02 '20 at 18:40

0 Answers0