Skip to content

v1.3

Choose a tag to compare

@gabikadlecova gabikadlecova released this 05 Dec 11:02
· 2 commits to master since this release
e7c82a2

The code was modified so that it is easier to reproduce the original results - before, only the code structure was the same, but the hyperparameters were different and the optimizer was SGD - there were difficulties with making RMSProp training work.

Now the networks can be successfully trained with RMSProp and with the same hyperparameters as in the paper.

  • Added reproducibility section to the readme
  • Hyperparameters were modified so that they match those from the NAS-Bench-101 paper
  • TensorFlow version of RMSProp is supported
  • Gradient clipping can be turned off

Special thanks to @longerhost for helping to reproduce the original training!