index
:
tensorflow
master
machine learning framework
about
summary
refs
log
tree
commit
diff
homepage
log msg
author
committer
range
path:
root
/
tensorflow
/
contrib
/
quantize
Commit message (
Expand
)
Author
Age
...
*
Add support for ResourceVariable weights to the quantization rewriter.
Suharsh Sivakumar
2018-03-07
*
Fix README formatting.
Suharsh Sivakumar
2018-03-06
*
Ensure folding of batch norms is idempotent.
Suharsh Sivakumar
2018-03-01
*
Ensure that final layer of networks (which doesn't have an activation) get co...
Suharsh Sivakumar
2018-02-21
*
Add a small test to ensure that rewrites are idempotent.
Suharsh Sivakumar
2018-02-20
*
Update contrib/quantize docs to add description of how to use rewrites.
Suharsh Sivakumar
2018-02-20
*
Make the default values for experimental and non experimental apis match.
Suharsh Sivakumar
2018-02-15
*
Fix incorrect is_training parameter.
Suharsh Sivakumar
2018-02-13
*
Automated g4 rollback of changelist 185420228
Suharsh Sivakumar
2018-02-12
*
Add tests for visible api arguments in quantize_graph.
Suharsh Sivakumar
2018-02-12
*
Also add quantization step node to MODEL_VARIABLES collection.
Suharsh Sivakumar
2018-02-12
*
Fix some doc strings that were accidentally removed.
Suharsh Sivakumar
2018-02-09
*
Add our own "global step" called quantization_step to avoid needing to reset ...
Suharsh Sivakumar
2018-02-08
*
Updated API for quantize_graph: Programmable quant_delay to determine start o...
Raghuraman Krishnamoorthi
2018-02-08
*
Make quantization rewrites happen in place.
Suharsh Sivakumar
2018-02-08
*
Generalize quantization rewrite to not rely on names.
Suharsh Sivakumar
2018-02-07
*
Make fold batch norm code use OneofPattern and rearrange functions to (maybe)...
Suharsh Sivakumar
2018-02-05
*
Add functionality to fold batch norm (supporting both fused and unfused batch...
Raghuraman Krishnamoorthi
2018-02-01
*
Update graph_matcher to include OneofPattern.
Suharsh Sivakumar
2018-01-31
*
Introduce experimental quantize training and eval apis.
Suharsh Sivakumar
2018-01-24
*
Fold FuseBatchNorm correctly.
Suharsh Sivakumar
2017-12-21
*
With fused batch norm, collect the tangle of nodes used for folding BN into B...
A. Unique TensorFlower
2017-12-14
*
Delete trailing whitespace
A. Unique TensorFlower
2017-11-27
*
Modify QuantizeAddContexts so that ops are added deterministically. This is n...
A. Unique TensorFlower
2017-11-17
*
Further BUILD cleanup in contrib/...
A. Unique TensorFlower
2017-11-10
*
Create documentation for retrain.py to describe addition of fixed point layer.
A. Unique TensorFlower
2017-11-10
*
Modify quantization to support add ops that occur after all quantizable types...
A. Unique TensorFlower
2017-11-10
*
MovingAvgQuantize and LastValueQuantize should use the updated value from the...
Suharsh Sivakumar
2017-11-10
*
Make quant_delay work even if user didn't create global step.
Suharsh Sivakumar
2017-11-10
*
Modify quantization to support add ops that occur after Conv2D
A. Unique TensorFlower
2017-10-31
*
BUILD cleanup in contrib/...
A. Unique TensorFlower
2017-10-30
*
Allow device specification for variables added by quantize graph rewriter.
Suharsh Sivakumar
2017-10-25
*
Remove name_scope from convolutional calls.
A. Unique TensorFlower
2017-10-23
*
Add support for fused batch norm to fake quantize rewriter.
Suharsh Sivakumar
2017-10-19
*
Batch norm folding immediately fails if FusedBatchNorm ops are present.
A. Unique TensorFlower
2017-10-16
*
Fix silly typo
Suharsh Sivakumar
2017-10-04
*
quantize API and copy and modify quantize mangle script to allow open sourcin...
Suharsh Sivakumar
2017-10-02
[prev]