Closed dylanrandle closed 4 years ago
@jlaasri This discussion seems very useful: quark0/darts#3
Seems like a useful paper: Random Search and Reproducibility for Neural Architecture Search
See https://github.com/capstone2019-neuralsearch/darts/commit/ebe158ccd36dedc2ac69ba6153ddfdbbb274c894.
The script is still not totally general but it produces comparable genotypes to what we've produced so far.
See branch "random_search" of darts repo.
What we can do now:
python random_search.py N --arg_example1 50 -arg_example2 300 ...
This will run "train.py" N times with N different random cells. All the arguments after "N" are directly passed to "train.py". In practice, this code will run the following command N times:
python train.py --random --arg_example1 50 -arg_example2 300 ...
.
Also, when running train.py, the genotype is saved to genotype.arch for easy access.
Done with random_search*.py
Implement random search over the genotype object, such that we can use it for comparison