This repository was archived by the owner on Jan 10, 2025. It is now read-only.
New method to set shape of model inputs#8
Open
fuzhenxin wants to merge 1 commit intohuggingface:masterfrom
Open
New method to set shape of model inputs#8fuzhenxin wants to merge 1 commit intohuggingface:masterfrom
fuzhenxin wants to merge 1 commit intohuggingface:masterfrom
Conversation
|
Thank you. Can confirm this is working and necessary in TF >=2.2 |
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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
For tensorflow>=2.2.0, the model._set_inputs failed in
tflite-android-transformers/models_generation/gpt2.py
Line 7 in dcd6da1
The following error will happen when running in Android:
java.lang.IllegalStateException: Internal error: Unexpected failure when preparing tensor allocations: tensorflow/lite/kernels/kernel_util.cc:249 d1 == d2 || d1 == 1 || d2 == 1 was not true.For tensorflow<=2.1.0, the error will not happen.
The added code set inputs shape of model by adding an additional layer, and it works for both tensorflow>=2.2 and tensorflow<2.2