[Frontend][TFLite] Fix quantized pad value for convolution #4807
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
* zero padding can't be done directly if the model is quantized since pad=0 will have different meaning in uint8 space
Contributor
|
Excellent find! I missed this somehow. I think the current test case failure might be because we give random input to a quantized network, and this leads to values being close to each other in the final output. We can try giving a real input to the quantized network, and then check if the label is present in top 5. |
Contributor
|
Let me take a look at this. You might have to wait for sometime as I am little busy, but I will get to it within 2 weeks. |
Contributor
This was referenced Feb 5, 2020
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Zero-padding can't be done directly in case the model is quantized, so we have to set
pad_value = zero_point