Difference between GDAS variants
D-X-Y opened this issue · comments
Xuanyi Dong 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])
Xuanyi Dong commented
Make a commitment to ablatively study this issue.
Xuanyi Dong 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.