Ubuntu L4T User Guide - Revision history

Daniel.hung at 06:35, 6 May 2020

2020-05-06T06:35:28Z

2020-02-04T01:54:21Z

2019-12-09T08:28:58Z

2019-12-09T08:26:43Z

2019-12-05T05:27:59Z

2019-12-03T09:14:38Z

2019-12-03T08:51:25Z

2019-12-03T08:06:59Z

2019-12-03T07:07:42Z

2019-12-03T06:58:29Z

@@ Line 38: / Line 38: @@
 '''Note:''' You will need a nVidia developer account for access.
-After download complete, double click the DEB file to install.
+After download complete, double click the DEB file to install, or you can run `sudo dpkg -i sdkmanager-xxx.deb`
 [[File:Sdkmamanger install.png|800px|Sdkmamanger_install]]
@@ Line 57: / Line 57: @@
 '''Note: '''Please <span style="color:#FF0000">DO NOT</span> check the "''Jetson OS''" item. It will generate and flash TX2 demo image into your device.
 '''STEP 03:''' After download process is done, you need to input the IP address of your TX2 device. It will install SDK via network.

@@ Line 89: / Line 89: @@
   $ vim deepstream_app_config_yoloV3.txt
-  uri=[file:///home/advrisc/Videos/2014.mp4 file:///home/advrisc/Videos/2014.mp4]
+  uri=[file:///home/advrisc/Videos/test.mp4 file:///home/advrisc/Videos/test.mp4]
 === <span style="color:#0070c0">FasterRCNN</span> ===

@@ Line 57: / Line 57: @@
 '''Note: '''Please <span style="color:#FF0000">DO NOT</span> check the "''Jetson OS''" item. It will generate and flash TX2 demo image into your device.
 '''STEP 03:''' After download process is done, you need to input the IP address of your TX2 device. It will install SDK via network.
@@ Line 69: / Line 65: @@
 [[File:Tx2-sdk-step3-sdk.png|800px|Tx2-sdk-step3-sdk]]
 '''STEP 04: '''When you go to this step, it's done!

@@ Line 4: / Line 4: @@
 Ubuntu 18.04 (recommended) or 16.04
 == <span style="color:#0070c0">Force Recovery Mode</span> ==
@@ Line 34: / Line 38: @@
 '''Note:''' You will need a nVidia developer account for access.
-After download complete, install via dpkg.
+After download complete, double click the DEB file to install.
- $ sudo dpkg -i sdkmanager_0.9.14-4964_amd64.deb
+[[File:Sdkmamanger install.png|800px|Sdkmamanger_install]]
 Then, you're able to run SDK manager.
@@ Line 53: / Line 57: @@
 '''Note: '''Please <span style="color:#FF0000">DO NOT</span> check the "''Jetson OS''" item. It will generate and flash TX2 demo image into your device.
 '''STEP 03:''' After download process is done, you need to input the IP address of your TX2 device. It will install SDK via network.

← Older revision		Revision as of 05:27, 5 December 2019
Line 14:		Line 14:

	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.		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 '''<span style="color:#0000F0">0955:7c18</span> NVidia Corp'''.

	== <span style="color:#0070c0">Flash Pre-built Image</span> ==		== <span style="color:#0070c0">Flash Pre-built Image</span> ==

@@ Line 53: / Line 53: @@
 '''STEP 03:''' After download process is done, you need to input the IP address of your TX2 device. It will install SDK via network.
-[[File:Tx2-sdk-step3-ip.png|400px|Tx2-sdk-step3-ip]]
+[[File:Tx2-sdk-step3-ip.png|500px|Tx2-sdk-step3-ip]]
 It will take several minutes to finish the installation.
@@ Line 67: / Line 67: @@
 In this section, we setup and run demo applications on TX2 target device.
-Export deepstream sdk root first.
+Open '''Terminal '''program and export deepstream sdk root first.
   $ export DS_SDK_ROOT="/opt/nvidia/deepstream/deepstream-4.0"

@@ Line 102: / Line 102: @@
   $ cp /usr/src/tensorrt/data/ssd/ssd_coco_labels.txt .
   $ pip install tensorflow-gpu
   $ wget [http://download.tensorflow.org/models/object_detection/ssd_inception_v2_coco_2017_11_17.tar.gz http://download.tensorflow.org/models/object_detection/ssd_inception_v2_coco_2017_11_17.tar.gz]
@@ Line 114: / Line 113: @@
   $ cd ..
   $ make -C nvdsinfer_custom_impl_ssd

@@ Line 41: / Line 41: @@
 Log in with your nVidia developer account, and you can see the STEP 01 page.
-[[File:Tx2-sdk-step1.png|800px|RTENOTITLE]]
+'''STEP 01:''' Set "''Target Hardware''" to "''Jetson TX2 P3310''", and select target OS you want to install. Here, we choose 4.2.2.
 = Demo =

@@ Line 64: / Line 64: @@
 Setup:
-  $ cd $DS_SDK_ROOT/sources/objectDectector_FasterRCNN
+  $ cd $DS_SDK_ROOT/sources/objectDetector_FasterRCNN
-  $ wget --no-check-certificate  [https://dl.dropboxusercontent.com/s/06ii098bu51d139/faster_rcnn_models.tgz?dl=0 https://dl.dropboxusercontent.com/s/06ii098bu51d139/faster_rcnn_models.tgz?dl=0]  -O faster-rcnn.tgz
+  $ wget --no-check-certificate  [https://dl.dropboxusercontent.com/s/o6ii098bu51d139/faster_rcnn_models.tgz?dl=0 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 .
@@ Line 79: / Line 79: @@
 Setup:
-  $ cd $DS_SDK_ROOT/sources/objectDectector_SSD
+  $ cd $DS_SDK_ROOT/sources/objectDetector_SSD
   $ cp /usr/src/tensorrt/data/ssd/ssd_coco_labels.txt .
@@ Line 104: / Line 104: @@
 Setup:
-  $ cd $DS_SDK_ROOT/sources/objectDectector_Yolo
+  $ cd $DS_SDK_ROOT/sources/objectDetector_Yolo
   $ ./prebuild.sh
   $ export CUDA_VER=10.0

@@ Line 26: / Line 26: @@
 == <span style="color:#0070c0">Install SDK Components</span> ==
 Download the SDK Manager for '''Jetson TX2 series''' from [https://developer.nvidia.com/embedded/jetpack JetPack website].
-You will need a nVidia developer account for access.
+'''Note:''' You will need a nVidia developer account for access.
 After download complete, install via dpkg.
@@ Line 41: / Line 39: @@
   $ sdkmanager
-=== <span style="color:#0070c0">Installation</span> ===
+Log in with your nVidia developer account, and you can see the STEP 01 page.
 = Demo =