Skip to content

Instantly share code, notes, and snippets.

@lambdaprime
lambdaprime / MXNET with CUDA compute capability 21.md
Last active April 15, 2019 04:48
How to run MXNET on GPU NVidia Fermi with Compute capability 2.1

How to run MXNET on GPU NVidia Fermi with Compute capability 2.1

MXNET dropped support of old GPU cards. The oldest version 0.11.0 available from here will not work on Fermi because it requires __shfl_xor and other instructions which became available only with next version of GPU arch. The only version of MXNET which I managed to run is v0.9.5 with following 3rdparty dependencies:

  • mshadow - commit ce8422ba98fca3b41d0d33b930995a6d54ded0ff
  • nnvm - commit b279286304ac954098d94a2695bca599e832effb

Prereq

@lambdaprime
lambdaprime / libopencv_java320.md
Last active May 27, 2019 23:17
Bug in libopencv_java320

Following lines did not work for me:

Mat img = new Mat();
Dictionary dictionary = Aruco.getPredefinedDictionary(Aruco.DICT_7X7_50);
Aruco.drawMarker(dictionary, 1, 200, img);

The process crashed with:

#