diff options
| author |  A. Unique TensorFlower <gardener@tensorflow.org> | 2016-12-14 15:39:14 -0800 |
|---|---|---|
| committer | TensorFlower Gardener <gardener@tensorflow.org> | 2016-12-14 15:45:33 -0800 |
| commit | 811629aed466db32eeefbd60783e199d2fe154a9 (patch) | |
| tree | ec24e6450bb0711f5ddc549b0a73892403e59da5 | |
| parent | a7cd5f671eb2219a763fe2d77c38ca61bff23f04 (diff) | |
Add Tactivation attribute for QuantizedMatmul and QuantizedMatmulMinMax to explicitly notify which quantizedtype output would be produced by following activation function.
Change: 142073731
| -rw-r--r-- | tensorflow/core/ops/math_ops.cc | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/tensorflow/core/ops/math_ops.cc b/tensorflow/core/ops/math_ops.cc index 9e692ed0bc..6a1c285dbf 100644 --- a/tensorflow/core/ops/math_ops.cc +++ b/tensorflow/core/ops/math_ops.cc @@ -2245,6 +2245,7 @@ REGISTER_OP("QuantizedMatMul") .Attr("Toutput: quantizedtype = DT_QINT32") .Attr("transpose_a: bool = false") .Attr("transpose_b: bool = false") + .Attr("Tactivation: quantizedtype = DT_QUINT8") .SetShapeFn([](InferenceContext* c) { TF_RETURN_IF_ERROR(shape_inference::MatMulShape(c)); ShapeHandle unused; @@ -2275,6 +2276,8 @@ min_b: The float value that the lowest quantized `b` value represents. max_b: The float value that the highest quantized `b` value represents. min_out: The float value that the lowest quantized output value represents. max_out: The float value that the highest quantized output value represents. +Tactivation: The type of output produced by activation function + following this operation. )doc"); |