diff options
| author | Narumol Prangnawarat <narumol.prangnawarat@arm.com> | 2023-09-20 16:04:58 +0100 |
|---|---|---|
| committer | Narumol Prangnawarat <narumol.prangnawarat@arm.com> | 2023-09-26 15:32:19 +0100 |
| commit | a2135bb3737bd7c86c6ea9ed8df2272e5f3ebcb0 (patch) | |
| tree | 3a3b4b7ac8f3127bb64381e12f9380354688cb48 /samples | |
| parent | 4a43c9403306d10cd7905c9cbd1f4962655db001 (diff) | |
| download | armnn-a2135bb3737bd7c86c6ea9ed8df2272e5f3ebcb0.tar.gz | |
IVGCVSW-8053 Update TensorFlow and FlatBuffers versions on ArmNN guides
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I975cf4ccbddd1ea756e1d9f2148dcb8e320346f5
Diffstat (limited to 'samples')
| -rw-r--r-- | samples/ObjectDetection/Readme.md | 20 |
1 files changed, 10 insertions, 10 deletions
diff --git a/samples/ObjectDetection/Readme.md b/samples/ObjectDetection/Readme.md index 87a38b3ff7..2b3a8d3e04 100644 --- a/samples/ObjectDetection/Readme.md +++ b/samples/ObjectDetection/Readme.md @@ -20,8 +20,8 @@ with detections shown in bounding boxes, class labels and confidence. This example utilizes OpenCV functions to capture and output video data. 1. Public Arm NN C++ API is provided by Arm NN library. 2. For Delegate file mode following dependencies exist: -2.1 Tensorflow version 2.10 -2.2 Flatbuffers version 2.0.6 +2.1 Tensorflow version 2.14 +2.2 Flatbuffers version 23.5.26 2.3 Arm NN delegate library ## System @@ -97,7 +97,7 @@ Please see [find_opencv.cmake](./cmake/find_opencv.cmake) for implementation det ### Tensorflow Lite (Needed only in delegate file mode) -This application uses [Tensorflow Lite)](https://www.tensorflow.org/) version 2.10 for demonstrating use of 'armnnDelegate'. +This application uses [Tensorflow Lite)](https://www.tensorflow.org/) version 2.14 for demonstrating use of 'armnnDelegate'. armnnDelegate is a library for accelerating certain TensorFlow Lite operators on Arm hardware by providing the TensorFlow Lite interpreter with an alternative implementation of the operators via its delegation mechanism. You may clone and build Tensorflow lite and provide the path to its root and output library directories through the cmake @@ -106,13 +106,13 @@ For implementation details see the scripts FindTfLite.cmake and FindTfLiteSrc.cm The application links with the Tensorflow lite library libtensorflow-lite.a -#### Download and build Tensorflow Lite version. We currently use Tf 2.12 SHA which has a fix for the Cmake build. +#### Download and build Tensorflow Lite version. We currently use Tf 2.14 for the Cmake build. Example for Tensorflow Lite native compilation ```commandline sudo apt install build-essential git clone https://github.com/tensorflow/tensorflow.git cd tensorflow/tensorflow -git checkout 6f692f73cb2043b4a0b0446539cd8c15b3dd9220 +git checkout v2.14.0-rc1 mkdir build && cd build cmake ../lite -DTFLITE_ENABLE_XNNPACK=OFF make @@ -120,19 +120,19 @@ make ### Flatbuffers (needed only in delegate file mode) -This application uses [Flatbuffers)](https://google.github.io/flatbuffers/) version 1.12.0 for serialization +This application uses [Flatbuffers)](https://google.github.io/flatbuffers/) version 23.5.26 for serialization You may clone and build Flatbuffers and provide the path to its root directory through the cmake flag FLATBUFFERS_ROOT. Please see [FindFlatbuffers.cmake] for implementation details. The application links with the Flatbuffers library libflatbuffers.a -#### Download and build flatbuffers version 2.0.6 +#### Download and build flatbuffers version 23.5.26 Example for flatbuffer native compilation ```commandline -wget https://github.com/google/flatbuffers/archive/v2.0.6.tar.gz -tar xf v2.0.6.tar.gz -cd flatbuffers-2.0.6 +wget https://github.com/google/flatbuffers/archive/v23.5.26.tar.gz +tar xf v23.5.26.tar.gz +cd flatbuffers-23.5.26 mkdir install && cd install cmake .. -DCMAKE_INSTALL_PREFIX:PATH=`pwd` make install |