-
Notifications
You must be signed in to change notification settings - Fork 4.2k
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
Adding a fully connected visual encoder for super small visual input + tests #5351
Conversation
kernel_init=Initialization.KaimingHeNormal, | ||
kernel_gain=1.41, # Use ReLU gain | ||
), | ||
nn.LeakyReLU(), |
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.
We could use another activation here, but I think ReLU is enough.
|
||
|
||
@pytest.mark.parametrize( | ||
"vis_class_and_size", |
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.
nit: you should be able to do "vis_class, size"
here, and test_visual_encoder_trains(vis_class, size)
as the test definition. Not a big deal though.
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 did not know I could do that. Thanks!
Proposed change(s)
Adding a fully connected option to visual encoding.
Useful links (Github issues, JIRA tickets, ML-Agents forum threads etc.)
Types of change(s)
Checklist
Other comments