From be33acd75f8b2110914a583da01c65bbc77eae09 Mon Sep 17 00:00:00 2001 From: Georgios Pinitas Date: Mon, 7 Sep 2020 13:51:53 +0100 Subject: COMPMID-3645: Clarify graph examples' immutable governance Document that no structural or data alterations have been applied to any of the provided models. Signed-off-by: Georgios Pinitas Change-Id: I74e6baaec1fbb08f26b16b4d5dce4406bcf5aca8 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3938 Tested-by: Arm Jenkins Reviewed-by: Michele Di Giorgio Comments-Addressed: Arm Jenkins --- docs/03_scripts.dox | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'docs/03_scripts.dox') diff --git a/docs/03_scripts.dox b/docs/03_scripts.dox index efa6fa9813..7e16edfb0d 100644 --- a/docs/03_scripts.dox +++ b/docs/03_scripts.dox @@ -143,6 +143,11 @@ The arm_compute::utils::load_trained_data shows how one could load the weights and biases into tensor from the .npy file by the help of Accessor. @section validate_examples Validating examples + +Compute Library provides a list of graph examples that are used in the context of integration and performance testing. +The provenance of each model is part of its documentation and no structural or data alterations have been applied to any +of them unless explicitly specified otherwise in the documentation. + Using one of the provided scripts will generate files containing the trainable parameters. You can validate a given graph example on a list of inputs by running: -- cgit v1.2.1