[Quantization] Support for more ops (conv1d) #6731
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
|
@ZihengJiang I want to add more coverage for the quantizer, do we generally add unit tests when adding more ops or is this PR sufficient? |
|
@tmoreau89 It is ok if you have verified that this PR doesn't affect the accuracy of common quantized models |
|
I did a spot check on a model that we're quantizing. Also ran some validation over a CIFAR-10 model from MxNet. I'll change it to a PR for review. |
|
thanks @ZihengJiang @vinx13 PTAL! |
tmoreau89
changed the title
ZihengJiang
approved these changes
Oct 27, 2020
liangfu
approved these changes
Nov 3, 2020
vinx13
approved these changes
Nov 7, 2020
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Dec 2, 2020
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Dec 4, 2020
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Dec 4, 2020
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Outdated suggestions cannot be applied.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.
Quantization support for conv1d for custom model. Added additional ops to increase size of quantized subgraphs.