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
[DHNE] #139
[DHNE] #139
Conversation
openhgnn/experiment.py
Outdated
@@ -78,7 +79,7 @@ def __init__(self, model, dataset, task, | |||
if use_best_config: | |||
self.config = set_best_config(self.config) | |||
self.set_params(**kwargs) | |||
print(self) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we need to delete this line? @Zhanghyi
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Dont delete it. This line prints experiment information.
encodeds = [] | ||
decodeds = [] | ||
for i in range(3): | ||
encoded = torch.tanh(self.encodeds[i].to(self.device)(input_ids[i].to(self.device))) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I remember that this "to(self.device)" has been done in the "trainerflow", so do we really need parameter "device"?
Description
Checklist
Please feel free to remove inapplicable items for your PR.
Changes