diff options
author | Éanna Ó Catháin <eanna.ocathain@arm.com> | 2021-04-07 14:35:25 +0100 |
---|---|---|
committer | Jim Flynn <jim.flynn@arm.com> | 2021-05-07 09:11:52 +0000 |
commit | c6ab02a626e15b4a12fc09ecd844eb8b95380c3c (patch) | |
tree | 9912ed9cdb89cdb24483b22d6621ae30049ae321 /samples/ObjectDetection/Readme.md | |
parent | e813d67f86df41a238ff79b5c554ef5027f56576 (diff) | |
download | armnn-c6ab02a626e15b4a12fc09ecd844eb8b95380c3c.tar.gz |
MLECO-1252 ASR sample application using the public ArmNN C++ API.
Change-Id: I98cd505b8772a8c8fa88308121bc94135bb45068
Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com>
Diffstat (limited to 'samples/ObjectDetection/Readme.md')
-rw-r--r-- | samples/ObjectDetection/Readme.md | 5 |
1 files changed, 2 insertions, 3 deletions
diff --git a/samples/ObjectDetection/Readme.md b/samples/ObjectDetection/Readme.md index bceaa4b250..408917eebc 100644 --- a/samples/ObjectDetection/Readme.md +++ b/samples/ObjectDetection/Readme.md @@ -230,7 +230,6 @@ Once the application executable is built, it can be executed with the following * --preferred-backends: Takes the preferred backends in preference order, separated by comma. For example: CpuAcc,GpuAcc,CpuRef. Accepted options: [CpuAcc, CpuRef, GpuAcc]. Defaults to CpuRef **[OPTIONAL]** -* --help: Prints all the available options to screen ### Object Detection on a supplied video file @@ -379,8 +378,8 @@ tensor names and calling `GetNetworkOutputBindingInfo()`. Generic object detection pipeline has 3 steps to perform data pre-processing, run inference and decode inference results in the post-processing step. -See [`ObjDetectionPipeline`](./include/NetworkPipeline.hpp) and implementations for [`MobileNetSSDv1`](./include/NetworkPipeline.hpp) -and [`YoloV3Tiny`](./include/NetworkPipeline.hpp) for more details. +See [`ObjDetectionPipeline`](include/ObjectDetectionPipeline.hpp) and implementations for [`MobileNetSSDv1`](include/ObjectDetectionPipeline.hpp) +and [`YoloV3Tiny`](include/ObjectDetectionPipeline.hpp) for more details. #### Pre-processing the Captured Frame Each frame captured from source is read as an `cv::Mat` in BGR format but channels are swapped to RGB in a frame reader |