From 65dbfe190761131a5fc8df89fd5118639acdcf68 Mon Sep 17 00:00:00 2001 From: EunHo Lee <108073642+AdvancedUno@users.noreply.github.com> Date: Sat, 7 Jan 2023 06:11:23 +0900 Subject: [PATCH] Fix documentation typos (#14084) --- docs/build/eps.md | 4 ++-- docs/build/inferencing.md | 6 +++--- docs/build/training.md | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/build/eps.md b/docs/build/eps.md index 6fad85dea2..da36d5fadc 100644 --- a/docs/build/eps.md +++ b/docs/build/eps.md @@ -45,8 +45,8 @@ The onnxruntime code will look for the provider shared libraries in the same loc ### Prerequisites {: .no_toc } -* Install [CUDA](https://developer.nvidia.com/cuda-toolkit) and [cuDNN](https://developer.nvidia.com/cudnn) - * The path to the CUDA installation must be provided via the CUDA_PATH environment variable, or the `--cuda_home` parameter +* Install [CUDA](https://developer.nvidia.com/cuda-toolkit) and [cuDNN](https://developer.nvidia.com/cudnn). + * The path to the CUDA installation must be provided via the CUDA_PATH environment variable, or the `--cuda_home` parameter. * The path to the cuDNN installation (include the `cuda` folder in the path) must be provided via the cuDNN_PATH environment variable, or `--cudnn_home` parameter. The cuDNN path should contain `bin`, `include` and `lib` directories. * The path to the cuDNN bin directory must be added to the PATH environment variable so that cudnn64_8.dll is found. diff --git a/docs/build/inferencing.md b/docs/build/inferencing.md index b2c95ee114..2ffd8ff99d 100644 --- a/docs/build/inferencing.md +++ b/docs/build/inferencing.md @@ -272,7 +272,7 @@ There are a few options for building for ARM. *EASY, SLOW, RECOMMENDED* -This method rely on qemu user mode emulation. It allows you to compile using a desktop or cloud VM through instruction level simulation. You'll run the build on x86 CPU and translate every ARM instruction to x86. This is much faster than compiling natively on a low-end ARM device and avoids out-of-memory issues that may be encountered. The resulting ONNX Runtime Python wheel (.whl) file is then deployed to an ARM device where it can be invoked in Python 3 scripts. +This method relies on qemu user mode emulation. It allows you to compile using a desktop or cloud VM through instruction level simulation. You'll run the build on x86 CPU and translate every ARM instruction to x86. This is much faster than compiling natively on a low-end ARM device and avoids out-of-memory issues that may be encountered. The resulting ONNX Runtime Python wheel (.whl) file is then deployed to an ARM device where it can be invoked in Python 3 scripts. Here is [an example for Raspberrypi3 and Raspbian](https://github.com/microsoft/onnxruntime/tree/master/dockerfiles/README.md#arm-32v7). Note: this does not work for Raspberrypi 1 or Zero, and if your operating system is different from what the dockerfile uses, it also may not work. @@ -291,9 +291,9 @@ This option is very fast and allows the package to be built in minutes, but is c You can use [GCC](https://gcc.gnu.org/) or [Clang](http://clang.llvm.org/). Both work, but instructions here are based on GCC. In GCC terms: - * "build" describes the type of system on which GCC is being configured and compiled + * "build" describes the type of system on which GCC is being configured and compiled. * "host" describes the type of system on which GCC runs. - * "target" to describe the type of system for which GCC produce code + * "target" to describe the type of system for which GCC produce code. When not cross compiling, usually "build" = "host" = "target". When you do cross compile, usually "build" = "host" != "target". For example, you may build GCC on x86_64, then run GCC on x86_64, then generate binaries that target aarch64. In this case,"build" = "host" = x86_64 Linux, target is aarch64 Linux. diff --git a/docs/build/training.md b/docs/build/training.md index 3d86bceb15..f4e7024b87 100644 --- a/docs/build/training.md +++ b/docs/build/training.md @@ -110,6 +110,6 @@ The default AMD GPU build requires ROCm software toolkit installed on the system `.\build.bat --enable_training --use_dnnl` -Add `--build_wheel` to build the ONNX Runtime wheel +Add `--build_wheel` to build the ONNX Runtime wheel. -This will produce a .whl file in `build/Linux/RelWithDebInfo/dist` for ONNX Runtime Training +This will produce a .whl file in `build/Linux/RelWithDebInfo/dist` for ONNX Runtime Training.