Fix model loading from .keras files in Tensorflow 2.15 #1123
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
trainable weights is only available after calling super.build. This leads to errors when reading models from saved .keras files as number of parameters does not match. This can be solved by changing the order as proposed. In addition, the trainable weights of the layer are expected to be in front of the quantize wrapper weights
Calling super.build() of the layer to indicate that the layer was built. Previous version did not set the self.built=True flag and would lead to a mismatch between stored and expected weights when loading a .keras model
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
github-actions
bot
added
the
technique:qat
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Outdated suggestions cannot be applied.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.
When loading models from .keras files, quantize layer weight number does not match stored number of weights as layer is build twice.
In addition, the QuantizeWrapperV2 does not populate the base layer weights correctly as the order of calls seems off.