This repository has been archived by the owner on Sep 18, 2024. It is now read-only.
Compression support for tf.keras.Sequential #2887
Merged
Conversation
This file contains 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
liuzhe-lz
requested review from
QuanluZhang and
chicm-ms
and removed request for
QuanluZhang
79 tasks
chicm-ms
reviewed
Sep 14, 2020
| ret.update(_locate_layers(value, cur_path + [key])) | ||
| elif isinstance(value, tf.keras.layers.Layer): | ||
| ret[id(value)] = LayerInfo(value, cur_path + [key]) | ||
| def _instrument(layer, config_list, LayerWrapperClass, compressor): |
There was a problem hiding this comment.
Is it possible to move _instrument and other functions into Compressor class?
There was a problem hiding this comment.
Yes, of course. I just personally don't like heavy methods which are used in (and can only be used in) constructor. Because I think "partially constructed" objects can be confusing.
QuanluZhang
approved these changes
Sep 14, 2020
chicm-ms
approved these changes
Sep 15, 2020
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
"A little bit breaking" change:
Compressor.compress()no longer guarantees to return the original model.This is because
tf.keras.Sequentialis designed for read-only usage and therefore is too tricky to compress in place. So we create a newSequentialwith instrumented layers instead.