Uh oh!
There was an error while loading. Please reload this page.
[WIP][QNN] Quantized fully connected - #3597
Closed
shoubhik wants to merge 56 commits into
Closed
Conversation
Requantize converts one quantized tensor representation to another quantized representation. The PR has following implementation features - Requantize operator defined in qnn namespace - relay.qnn.requantize - Lowering of the requantize to exisiting Relay operators - Integer fixed point implementation of requantize - Two rounding modes - FE_UPWARDS (round towards infinity) and FE_AWAY_FROM_ZERO (std::round behavior) - Floating point implementation as well, that can act as reference or can be used for devices when FP32 computation is not used. - Unit test cases Relevant Issue - apache#2351 Credit to TFLite and GemmLowp to provide reference implementations.
Requantize converts one quantized tensor representation to another quantized representation. The PR has following implementation features - Requantize operator defined in qnn namespace - relay.qnn.requantize - Lowering of the requantize to exisiting Relay operators - Integer fixed point implementation of requantize - Two rounding modes - FE_UPWARDS (round towards infinity) and FE_AWAY_FROM_ZERO (std::round behavior) - Floating point implementation as well, that can act as reference or can be used for devices when FP32 computation is not used. - Unit test cases Relevant Issue - apache#2351 Credit to TFLite and GemmLowp to provide reference implementations.
# Conflicts: # include/tvm/relay/qnn/attrs.h # python/tvm/relay/qnn/op/qnn.py # src/relay/qnn/pass/qnn_lower.cc # src/relay/qnn/util.h
# Conflicts: # python/tvm/relay/qnn/op/qnn.py
# Conflicts: # src/relay/qnn/pass/qnn_lower.cc # src/relay/qnn/util.h
shoubhik
commented
Aug 15, 2019
ContributorAuthor
There is dependency on #3779. Once it is merged the test cases will pass. will wait for it, |
shoubhik
commented
Oct 1, 2019
ContributorAuthor
Another PR has been merged with these changes. |
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 freeto 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.
This PR is the implementation of pre-quantized fully connected op.