Update timm library to 0.4.12 #429
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
zurk
commented
Jul 2, 2021
| @@ -1,4 +1,4 @@ | |||
| torchvision>=0.3.0 | |||
| torchvision>=0.5.0 | |||
There was a problem hiding this comment.
| act_layer=Swish, | ||
| norm_kwargs={}, # TODO: check |
There was a problem hiding this comment.
There is no more norm_kwargs and channel_multiplier options.
norm_kwargs was not used, so I just delete it, but in the case of channel_multiplier, you can still pass it shrough the new round_chs_fn argument.
| @@ -74,7 +74,7 @@ def load_state_dict(self, state_dict, **kwargs): | |||
| 'block': SelectiveKernelBasic, | |||
| 'layers': [2, 2, 2, 2], | |||
| 'zero_init_last_bn': False, | |||
| 'block_args': {'sk_kwargs': {'min_attn_channels': 16, 'attn_reduction': 8, 'split_input': True}} | |||
| 'block_args': {'sk_kwargs': {'rd_ratio': 1/8, 'split_input': True}} | |||
There was a problem hiding this comment.
attn_reductionwas changed tord_ratioand the value is inversed. So oldattn_reductionequals to new1 / rd_ratio
- There is no more
min_attn_channels. I did not find an easy way to keep it here and I think it is fine to just delete it.
|
It works for me,timm 0.4.12 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Closes issues #417 #424
Closes PR #418
Hi @qubvel!
I would like to update of
timmlibrary to make it compatible with the latest torch versions.All changes in code need to be done to fix test errors. I explain each line to help understand what I did in self-review.
Please, if you OK with this PR merge it and publish a new (I believe v0.2.0) version of the
segmentation-models-pytorchpackage.