Giters

D-X-Y / AutoDL-Projects

Automated deep learning algorithms implemented in PyTorch.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Difference between GDAS variants

D-X-Y opened this issue · comments

commented

Which Algorithm
GDAS: Searching for A Robust Neural Architecture in Four GPU Hours

Describe the Question
In search_cells.py, there are two kinds of GDAS implementations:

  • First, self._ops[index](x) * weights[index]
  • Second, weights[_ie] * edge(nodes[j]) if _ie == argmaxs else weights[_ie] for _ie, edge in enumerate(self.edges[node_str])
commented

Make a commitment to ablatively study this issue.

commented

TODO:

Run
python ./exps/NATS-algos/search-cell.py --dataset cifar10 --data_path $TORCH_HOME/cifar.python --algo gdas_v1 --rand_seed 777
and
python ./exps/NATS-algos/search-cell.py --dataset cifar10 --data_path $TORCH_HOME/cifar.python --algo gdas --rand_seed 777 to see the performance difference.