From d53202bc9498a9045747282530380f92b4d66a00 Mon Sep 17 00:00:00 2001 From: "A. Unique TensorFlower" Date: Mon, 5 Feb 2018 14:38:07 -0800 Subject: [PATCH] [XLA] Fix documentation for Clamp. PiperOrigin-RevId: 184588630 --- tensorflow/docs_src/performance/xla/operation_semantics.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tensorflow/docs_src/performance/xla/operation_semantics.md b/tensorflow/docs_src/performance/xla/operation_semantics.md index 1e9b8b3..f865c30 100644 --- a/tensorflow/docs_src/performance/xla/operation_semantics.md +++ b/tensorflow/docs_src/performance/xla/operation_semantics.md @@ -252,7 +252,7 @@ Clamps an operand to within the range between a minimum and maximum value. Given an operand and minimum and maximum values, returns the operand if it is in the range between the minimum and maximum, else returns the minimum value if the operand is below this range or the maximum value if the operand is above this -range. That is, `clamp(a, x, b) = max(min(a, x), b)`. +range. That is, `clamp(a, x, b) = min(max(a, x), b)`. All three arrays must be the same shape. Alternately, as a restricted form of [broadcasting](broadcasting.md), `min` and/or `max` can be a scalar of type `T`. -- 2.7.4