Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Suggestion for Neural Architecture Search with Reinforcement Learning #339

Merged
merged 24 commits into from
Feb 21, 2019
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 0 additions & 7 deletions pkg/suggestion/nasrl_service.py
Original file line number Diff line number Diff line change
Expand Up @@ -125,11 +125,6 @@ def GetSuggestions(self, request, context):
time.sleep(20)
result = self.GetEvaluationResult(request.study_id)

# This lstm cell is designed to maximize the metrics
# However, if the user want to minimize the metrics, we can take the negative of the result
if self.opt_direction == api_pb2.MINIMIZE:
result = -result

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why delete above?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry, I made a mistake. Should delete the code above that. Already fixed

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ok, thanks

loss, entropy, lr, gn, bl, skip, _ = sess.run(
fetches=run_ops,
feed_dict={valid_acc: result})
Expand Down Expand Up @@ -208,8 +203,6 @@ def GetEvaluationResult(self, studyID):
return float(ml.values[-1].value)

# TODO: add support for multiple trials
self.logger.warning("Error. No trial has completed.")
return None


def _get_search_space(self, studyID):
Expand Down