From 1098538cacf6badc040804a99627278510fd8912 Mon Sep 17 00:00:00 2001 From: Linyan Mei Date: Thu, 28 Sep 2023 05:14:19 +0200 Subject: [PATCH] fix a typo (also a test) --- docs/source/getting-started.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/getting-started.rst b/docs/source/getting-started.rst index e1fcf578..f050eb9a 100644 --- a/docs/source/getting-started.rst +++ b/docs/source/getting-started.rst @@ -9,7 +9,7 @@ As a first step, we use it to automatically optimize the way a NN is mapped onto First run ========= -The NN we are going to use for this first run is AlexNet. We provide an `onnx `_ model of this network in ``zigzag/inputs/examples/workload/alexnet.onnx``. The model has been shape inferred, which means that besied the input and output tensor shapes, all intermediate tensor shapes have been inferred, which is information required by ZigZag. +The NN we are going to use for this first run is AlexNet. We provide an `onnx `_ model of this network in ``zigzag/inputs/examples/workload/alexnet.onnx``. The model has been shape inferred, which means that beside the input and output tensor shapes, all intermediate tensor shapes have been inferred, which is information required by ZigZag. .. warning:: ZigZag requires an inferred onnx model, as it needs to know the shapes of all intermediate tensors to correctly infer the layer shapes. You can find more information on how to infer an onnx model `here `_.