From 6e97c82c97de32ee84c28e7ccf73a06471f62eb0 Mon Sep 17 00:00:00 2001 From: Roman Kazantsev Date: Wed, 5 Apr 2023 23:01:02 +0400 Subject: [PATCH] [Spec] Fix Interpolate specification: input index port (#16762) --- docs/ops/image/Interpolate_11.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/ops/image/Interpolate_11.md b/docs/ops/image/Interpolate_11.md index 14b37383a2a..05014c8a153 100644 --- a/docs/ops/image/Interpolate_11.md +++ b/docs/ops/image/Interpolate_11.md @@ -91,7 +91,7 @@ * **2**: `scales_or_sizes` - 1D tensor containing the data used to calculate the spatial output shape. The number of elements must match the number of values in the `axes` input tensor, the order needs to match as well. The type of this input tensor is either *T_SCALES* or *T_SIZES* depending on the value of the `shape_calculation_mode` attribute. **Required.** -* **4**: `axes` - 1D tensor of type *T_AXES* specifying dimension indices where interpolation is applied, and `axes` is any unordered list of indices of different dimensions of input tensor, e.g. `[0, 4]`, `[4, 0]`, `[4, 2, 1]`, `[1, 2, 3]`. These indices should be non-negative integers from `0` to `rank(image) - 1` inclusively. Other dimensions do not change. The order of elements in `axes` attribute matters and is mapped directly to the elements in the 2nd input `scales_or_sizes`. **Optional** with default value `[X,...,rank(image) - 1]` pointing to the spatial dimensions of the input image. The number of the default axes matches the number of elements in the `scales_or_sizes` input tensor. +* **3**: `axes` - 1D tensor of type *T_AXES* specifying dimension indices where interpolation is applied, and `axes` is any unordered list of indices of different dimensions of input tensor, e.g. `[0, 4]`, `[4, 0]`, `[4, 2, 1]`, `[1, 2, 3]`. These indices should be non-negative integers from `0` to `rank(image) - 1` inclusively. Other dimensions do not change. The order of elements in `axes` attribute matters and is mapped directly to the elements in the 2nd input `scales_or_sizes`. **Optional** with default value `[X,...,rank(image) - 1]` pointing to the spatial dimensions of the input image. The number of the default axes matches the number of elements in the `scales_or_sizes` input tensor. **Outputs**