diff options
| author | Mike Kelly <mike.kelly@arm.com> | 2021-12-20 13:27:04 +0000 |
|---|---|---|
| committer | Jim Flynn <jim.flynn@arm.com> | 2021-12-21 09:51:46 +0000 |
| commit | 2ca9a14b04f31f6a029b2747d39ee49a682eddab (patch) | |
| tree | 24d45b02c6ed0a82f265749b4f5d5a7317b5fbfb /delegate/DelegateQuickStartGuide.md | |
| parent | bc2e217d90064820e272a5d178c35657a659a864 (diff) | |
| download | armnn-2ca9a14b04f31f6a029b2747d39ee49a682eddab.tar.gz | |
IVGCVSW-6668 Updating build guides
* Updated build guides to refer to get_compute_library.sh and get_tensorflow.sh
* Corrected TensorFlow Version in guides was v2.5.1 but release notes say v2.5.0
* Reordered command sequence to ensure that Arm NN is downloaded and ready
before downloading TensorFlow or Arm Compute Library
* Fixed hyperlinks in MD files
* Added whitespace to fix MD formatting.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Iabc309cbbd41d969eb1e11e9dd33a0b1da39a27b
Diffstat (limited to 'delegate/DelegateQuickStartGuide.md')
| -rw-r--r-- | delegate/DelegateQuickStartGuide.md | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/delegate/DelegateQuickStartGuide.md b/delegate/DelegateQuickStartGuide.md index ed462b2a1b..b581bce62c 100644 --- a/delegate/DelegateQuickStartGuide.md +++ b/delegate/DelegateQuickStartGuide.md @@ -47,7 +47,7 @@ you can download the binaries [here](https://github.com/ARM-software/armnn/relea We recommend creating a virtual environment for this tutorial. For the following code to work python3 is needed. Please also check the documentation of the TfLite version you want to use. There might be additional prerequisites for the python -version. We will use Tensorflow Lite 2.5.1 for this guide. +version. We will use Tensorflow Lite 2.5.0 for this guide. ```bash # Install python3 (We ended up with python3.5.3) and virtualenv sudo apt-get install python3-pip @@ -71,7 +71,7 @@ mobile and embedded devices. The TfLite [website](https://www.tensorflow.org/lite/guide/python) shows you two methods to download the `tflite_runtime` package. In our experience, the use of the pip command works for most systems including debian. However, if you're using an older version of Tensorflow, you may need to build the pip package from source. You can find more information [here](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/tools/pip_package/README.md). -But in our case, with Tensorflow Lite 2.5.1, we can install through: +But in our case, with Tensorflow Lite 2.5.0, we can install through: ``` pip3 install --extra-index-url https://google-coral.github.io/py-repo/ tflite_runtime |