Difference between revisions of "Deploying Deep Learning"
m |
m |
||
| (5 intermediate revisions by the same user not shown) | |||
| Line 6: | Line 6: | ||
Reference : https://github.com/dusty-nv/jetson-inference/blob/L4T-R32.5.0/docs/building-repo-2.md | Reference : https://github.com/dusty-nv/jetson-inference/blob/L4T-R32.5.0/docs/building-repo-2.md | ||
| + | |||
| + | ''' Build Jetson Inference ''' | ||
| + | |||
| + | Here's a condensed form of the commands to build/install the project directly on your Jetson. | ||
<pre>$ sudo apt-get update | <pre>$ sudo apt-get update | ||
| Line 22: | Line 26: | ||
Reference : https://github.com/dusty-nv/jetson-inference/blob/L4T-R32.5.0/docs/imagenet-console-2.md | Reference : https://github.com/dusty-nv/jetson-inference/blob/L4T-R32.5.0/docs/imagenet-console-2.md | ||
| − | + | ||
''' Using the ImageNet Program on Jetson ''' | ''' Using the ImageNet Program on Jetson ''' | ||
| Line 30: | Line 34: | ||
</pre> | </pre> | ||
| − | Next, let's classify an example image with the imagenet program, using Python | + | Next, let's classify an example image with the imagenet program, using Python.These images will then be easily viewable from your host device in the jetson-inference/data/images/test directory. |
| − | <pre>$ ./imagenet.py images/strawberry_0.jpg images/test/ | + | <pre>$ ./imagenet.py images/strawberry_0.jpg images/test/strawberry.jpg |
</pre> | </pre> | ||
[[File:Identify strawberry.jpg|thumb|left|strawberry]] | [[File:Identify strawberry.jpg|thumb|left|strawberry]] | ||
| + | <br/> | ||
<br/> | <br/> | ||
<br/> | <br/> | ||
| Line 52: | Line 57: | ||
''' Detecting Objects from Images ''' | ''' Detecting Objects from Images ''' | ||
| − | + | Make sure your terminal is located in the aarch64/bin directory. | |
<pre>$ cd jetson-inference/build/aarch64/bin | <pre>$ cd jetson-inference/build/aarch64/bin | ||
| Line 59: | Line 64: | ||
Here are some examples of detecting pedestrians in images with the default SSD-Mobilenet-v2 model. | Here are some examples of detecting pedestrians in images with the default SSD-Mobilenet-v2 model. | ||
| − | <pre>$ ./detectnet.py --network=ssd-mobilenet-v2 images/peds_0.jpg images/test/ | + | <pre>$ ./detectnet.py --network=ssd-mobilenet-v2 images/peds_0.jpg images/test/person.jpg |
</pre> | </pre> | ||
| Line 76: | Line 81: | ||
''' Processing Video Files ''' | ''' Processing Video Files ''' | ||
| − | You can also process videos from disk. There are some test videos found on your Jetson under /usr/share/visionworks/sources/data | + | You can also process videos from disk. There are some test videos found on your Jetson under /usr/share/visionworks/sources/data . |
| − | <pre>./detectnet.py /usr/share/visionworks/sources/data/pedestrians.mp4 images/test/ | + | <pre>$ ./detectnet.py /usr/share/visionworks/sources/data/pedestrians.mp4 images/test/pedestrians_identify.mp4 |
</pre> | </pre> | ||
[[File:Pedestrians.png|thumb|left|pedestrians]] | [[File:Pedestrians.png|thumb|left|pedestrians]] | ||
Latest revision as of 08:28, 14 October 2022
Contents
Linux Version
Ubuntu 18.04
L4T-R32.5.0
Build Deep Learning on Jeston
Reference : https://github.com/dusty-nv/jetson-inference/blob/L4T-R32.5.0/docs/building-repo-2.md
Build Jetson Inference
Here's a condensed form of the commands to build/install the project directly on your Jetson.
$ sudo apt-get update $ sudo apt-get install git cmake libpython3-dev python3-numpy $ git clone --recursive https://github.com/dusty-nv/jetson-inference $ cd jetson-inference $ mkdir build $ cd build $ cmake ../ $ make -j$(nproc) $ sudo make install $ sudo ldconfig
Classifying Images with ImageNet
Reference : https://github.com/dusty-nv/jetson-inference/blob/L4T-R32.5.0/docs/imagenet-console-2.md
Using the ImageNet Program on Jetson
After building the project, make sure your terminal is located in the aarch64/bin directory.
$ cd jetson-inference/build/aarch64/bin
Next, let's classify an example image with the imagenet program, using Python.These images will then be easily viewable from your host device in the jetson-inference/data/images/test directory.
$ ./imagenet.py images/strawberry_0.jpg images/test/strawberry.jpg
Locating Objects with DetectNet
Reference : https://github.com/dusty-nv/jetson-inference/blob/L4T-R32.5.0/docs/detectnet-console-2.md
Detecting Objects from Images
Make sure your terminal is located in the aarch64/bin directory.
$ cd jetson-inference/build/aarch64/bin
Here are some examples of detecting pedestrians in images with the default SSD-Mobilenet-v2 model.
$ ./detectnet.py --network=ssd-mobilenet-v2 images/peds_0.jpg images/test/person.jpg
Processing Video Files
You can also process videos from disk. There are some test videos found on your Jetson under /usr/share/visionworks/sources/data .
$ ./detectnet.py /usr/share/visionworks/sources/data/pedestrians.mp4 images/test/pedestrians_identify.mp4
