Exclude Conv op from quantization in ort-quantize.py
#550
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
By default `quantize_dynamic` will replace `Conv` with `ConvInteger`. RTen doesn't support this operator yet and ONNX Runtime doesn't support the operator with the particular combination of data types that `quantize_dynamic` generates (u8 input, i8 weights). Hence omit this from the quantized op types for now.
robertknight
force-pushed
the
ort-quantize-exclude-conv
branch
from
a5fff2a to
8e888d6
Compare
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Outdated suggestions cannot be applied.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.
By default
quantize_dynamicwill replaceConvwithConvInteger. RTen doesn't support this operator yet and ONNX Runtime doesn't support the operator with the particular combination of data types thatquantize_dynamicgenerates (u8 input, i8 weights) (see issues mentioned in comments). Hence omit this from the quantized op types for now.