v1.3.1

• num_workers was not set on train-set only cifar
• set all default hyperparams inside train and Network

v1.3

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!

v1.2.3

• fixed a bug where the model couldn't be cast to double (torch.zeros was replaced by torch.zeros_like)
  • by @abhash-er

1.2.2

• fixed an error in in place modification that resulted in backward pass crashing for some architectures (a36d7a7)

1.2.1

• fixed inconsistencies in devices when training on cuda - torch.zeros() caused the problem

1.2

• fixed a bug in training - when optimizer was None, it wasn't set to sgd properly
• modified the code so that the networks can be passed to torch.jit.script()

1.1

• Updated the nasbench query example in the README
• More convenient checkpointing during training. Before, the checkpoint function had to have this signature:

checkpoint_func(network, metrics)

Since this version:

checkpoint_func(network, metrics, epoch number)

1.0

nasbench_pytorch 1.0

NASBench-PyTorch is now an installable package uploaded to Pypi. You can install it like this (working PyTorch installation is needed):

pip install nasbench_pytorch

What's Changed

• Refactor the project to a package-like structure by @gabrielasuchopar in #2