Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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
Add UNet 1d for RL model for planning + colab #105
Add UNet 1d for RL model for planning + colab #105
Changes from 6 commits
8d1a17c
84e94d7
f67b036
e42d1c0
2dd514e
b4c6188
c53bba9
effcbdb
7865231
35b0a43
9b1379d
e97a610
8642560
f58c915
ad8376d
3b08bea
aae2a9a
dd872af
9b67bb7
db012eb
4db6e0b
634a526
aebf547
305ecd8
42855b9
95d3a1c
6cbb73b
ffb7355
a6314f6
48a7414
3acddb5
713e8f2
268ebdf
daa05fb
ea5f231
4f7a3a4
d90b8b1
ad8b6cf
e06a4a4
99b2c81
de4b6e4
ef6ca1f
6e3485c
e6f1a83
c35a925
949b93a
2f6462b
a2dd559
39dff73
d5eedff
faeacd5
be25030
72b7ee8
cf76a2d
2290356
a061f7e
0c58758
691ddee
4948ca7
ac88677
ba204db
915c41e
c901889
becc803
9b8e5ee
3684a8c
ebdef16
a259aae
1f7702c
File filter
Filter by extension
Conversations
Jump to
There are no files selected for viewing
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.
Not a big fan of using blocks here as it makes it very hard to adapt the class to future models. Sorry this is a bit annoying to do when converting the checkpoint, but could we maybe instead call the layers
self.conv_in
andself.conv_out
? The idea here is that if in the future there are checkpoints which have an intermediate conv layer it'd be much easier to adapt this layer without breaking the previous checkpoitnsThere 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 think the shape should be
(batch, horizon, obs_dimension + action_dimension)
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.
Let's really try to mirror the design in
src/diffusers/models/unet_2d.py
hereThere 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'll try and make it work with the
get_block
function. The parameter re-naming script is getting quite ugly so we'll see how far I make it 🤗.