-
Notifications
You must be signed in to change notification settings - Fork 132
Tests for self attention using CumConcatLayer #590
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
Conversation
66cb35e
to
2337f50
Compare
2384c1b
to
cf604e1
Compare
626c35b
to
75b72db
Compare
6deb705
to
a406d3f
Compare
405218b
to
dc58c5a
Compare
This should be ready now. I left in |
There is also I did not check in detail, is this really exactly the same, or just similar? What is the difference? |
dc58c5a
to
90e780c
Compare
Oh okay, I missed that. The test case in this PR also checks that |
Hm, I don't know. It might be nice as an example. I would say leave it. |
Some tests for #391.
I didn't run any of this yet (so most likely buggy) because there is no implementation.
It still needs
CumConcatLayer
from #589, but also thecommon
arguments forDotLayer
from #569.Also, some way to set dim tags (e.g.
set_dim_tags: Dict[str, DimensionTag]
forReinterpretDataLayer
. I'm not sure, didn't we add this already somewhere?)We might also want more tests than this: e.g. some with positional encoding.