Ubuntu L4T User Guide

From ESS-WIKI
Jump to: navigation, search

Getting Started

Host Environment

Ubuntu 18.04 (recommended) or 16.04

[Prerequisite]

$ sudo apt-get install python

Force Recovery Mode

To enter force recovery mode, you can do:

1. Hold the Recovery key
2. Power on device
3. Wait for 5 seconds and you can release the Recovery key

Once it enters recovery mode successfully, the HDMI output should be disabled. Then, you have to connect a USB cable with TX2 device and PC. A new "nvidia apx" device will be detected on PC.

$ lsusb
Bus 003 Device 125: ID 0955:7c18 NVidia Corp.

Flash Pre-built Image

First, make sure your TX2 device is already in Force Recover mode, and USB cable is connected.

Then, execute the TX2_flash.sh script which you can find it in the release folder.

$ sudo ./TX2_flash.sh

After script is done, the target device will boot into OS automatically.

Install SDK Components

Download the SDK Manager for Jetson TX2 series from JetPack website.

Note: You will need a nVidia developer account for access.

After download complete, double click the DEB file to install, or you can run `sudo dpkg -i sdkmanager-xxx.deb`

Sdkmamanger_install

Then, you're able to run SDK manager.

$ sdkmanager

Log in with your nVidia developer account, and you can see the STEP 01 page.

STEP 01: Set "Target Hardware" to "Jetson TX2 P3310", and select target OS you want to install. Here, we choose 4.2.2.

Tx2-sdk-step1

STEP 02: Check the components you want, and continue.

Tx2-sdk-step2

Note: Please DO NOT check the "Jetson OS" item. It will generate and flash TX2 demo image into your device.

Note: You may need minimum 120GB free storage and 8GB RAM as prerequisite.

STEP 03: After download process is done, you need to input the IP address of your TX2 device. It will install SDK via network.

Tx2-sdk-step3-ip

It will take several minutes to finish the installation.

Tx2-sdk-step3-sdk

Note: If you see the warning dialog said it's taking longer than expected, please press Yes to continue installing.

Install_take_longer

STEP 04: When you go to this step, it's done!

Tx2-sdk-step4

Demo

In this section, we setup and run demo applications on TX2 target device.

Open Terminal program and export deepstream sdk root first.

$ export DS_SDK_ROOT="/opt/nvidia/deepstream/deepstream-4.0"

Deepstream Samples

There are 3 kinds of object detector demos in deepstream SDK.

To replace the video file, you can modify the corresponding config files. For example,

$ vim deepstream_app_config_yoloV3.txt
uri=file:///home/advrisc/Videos/test.mp4

FasterRCNN

Setup:

$ cd $DS_SDK_ROOT/sources/objectDetector_FasterRCNN
$ wget --no-check-certificate  https://dl.dropboxusercontent.com/s/o6ii098bu51d139/faster_rcnn_models.tgz?dl=0  -O faster-rcnn.tgz
$ tar zxvf  faster-rcnn.tgz  -C .  --strip-components=1  --exclude=ZF_*
$ cp /usr/src/tensorrt/data/faster-rcnn/faster_rcnn_test_iplugin.prototxt .

$ make -C nvdsinfer_custom_impl_fasterRCNN

Run:

$ deepstream-app -c deepstream_app_config_fasterRCNN.txt

SSD

Setup:

$ cd $DS_SDK_ROOT/sources/objectDetector_SSD

$ cp /usr/src/tensorrt/data/ssd/ssd_coco_labels.txt .
$ sudo apt-get install python-protobuf
$ pip install tensorflow-gpu

$ wget http://download.tensorflow.org/models/object_detection/ssd_inception_v2_coco_2017_11_17.tar.gz
$ tar zxvf ssd_inception_v2_coco_2017_11_17.tar.gz
$ cd ssd_inception_v2_coco_2017_11_17
$ python3 /usr/lib/python3.6/dist-packages/uff/bin/convert_to_uff.py \
    frozen_inference_graph.pb  -O NMS  -p /usr/src/tensorrt/samples/sampleUffSSD/config.py  -o sample_ssd_relu6.uff
$ cp sample_ssd_relu6.uff ../

$ cd ..
$ export CUDA_VER=10.0
$ make -C nvdsinfer_custom_impl_ssd

Run:

$ deepstream-app -c deepstream_app_config_ssd.txt

Yolo

Setup:

$ cd $DS_SDK_ROOT/sources/objectDetector_Yolo
$ ./prebuild.sh
$ export CUDA_VER=10.0
$ make -C nvdsinfer_custom_impl_Yolo

Run:

$ deepstream-app -c deepstream_app_config_yoloV3.txt
-OR-
$ deepstream-app -c deepstream_app_config_yoloV3_tiny.txt

Deepstream Reference Apps

In this repository, it provides some reference applications for video analytics tasks using TensorRT and DeepSTream SDK 4.0.

$ cd $DS_SDK_ROOT/sources/apps/sample_apps/
$ git clone https://github.com/NVIDIA-AI-IOT/deepstream_reference_apps.git
$ cd deepstream_reference_apps

back-to-back-detectors & anomaly

These two applications only support elementary h264 stream, not mp4 video file.

runtime_source_add_delete

Setup:

$ cd runtime_source_add_delete
$ make

Run:

$ ./deepstream-test-rt-src-add-del <uri>
$ ./deepstream-test-rt-src-add-del file://$DS_SDK_ROOT/samples/streams/sample_1080p_h265.mp4
$ ./deepstream-test-rt-src-add-del rtsp://127.0.0.1/video