Hello AI World - now supports Python and onboard training with PyTorch!

Hi all, just merged a large set of updates and new features into jetson-inference master:

  • Python API support for imageNet, detectNet, and camera/display utilities
  • Python examples for processing static images and live camera streaming
  • Support for interacting with numpy ndarrays from CUDA
  • Onboard re-training of ResNet-18 models with PyTorch
  • Example datasets: 800MB Cat/Dog and 1.5GB PlantCLEF
  • Camera-based tool for collecting and labeling custom datasets
  • Text UI tool for selecting/downloading pre-trained models
  • New pre-trained image classification models (on 1000-class ImageNet ILSVRC)
    • ResNet-18, ResNet-50, ResNet-101, ResNet-152
    • VGG-16, VGG-19
    • Inception-v4
  • New pre-trained object detection models (on 90-class MS-COCO)
    • SSD-Mobilenet-v1
    • SSD-Mobilenet-v2
    • SSD-Inception-v2
  • API Reference documentation for C++ and Python
  • Command line usage info for all examples, run with --help
  • Output of network profiler times, including pre/post-processing
  • Improved font rasterization using system TTF fonts

Screencast video - Realtime Object Detection in 10 Lines of Python Code on Jetson Nano


Here’s an object detection example in 10 lines of Python code using SSD-Mobilenet-v2 (90-class MS-COCO) with TensorRT, which runs at 25FPS on Jetson Nano on a live camera stream with OpenGL visualization:

import jetson.inference
import jetson.utils

net = jetson.inference.detectNet("ssd-mobilenet-v2")
camera = jetson.utils.gstCamera()
display = jetson.utils.glDisplay()

while display.IsOpen():
	img, width, height = camera.CaptureRGBA()
	detections = net.Detect(img, width, height)
	display.RenderOnce(img, width, height)
	display.SetTitle("Object Detection | Network {:.0f} FPS".format(1000.0 / net.GetNetworkTime()))

Thanks to all the beta testers of the new features from here on the forums!

Project Link…https://github.com/dusty-nv/jetson-inference/
Model Mirror…https://github.com/dusty-nv/jetson-inference/releases

Hi all, we’ve just posted a screencast tutorial for Hello AI World - check it out!

Realtime Object Detection in 10 Lines of Python Code on Jetson Nano


Hello everyone! I would like to work on your PlantClef project for the recognition of plants in parks … I would like to do this with my Ubuntu - nVidia 1080 ti pc. Can I do it with this too? or you just need the Jetson Nano. I have a Jetson Nano but I am currently using it for a video surveillance system etc …

Hi @steppi, you can do the training of the PlantCLEF image classification model on your GeForce 1080 Ti card in Ubuntu. If you install PyTorch on your desktop (see here) it should work just the same (I also do training on my Ubuntu PC).

As far as inference goes, the jetson-inference library is intended to be compiled/run on Jetson, but some folks have built it for x86 with relatively minor modification to the CMakeLists, ect.

Thank you so much for your answer! I have already installed PyTorch for a few days, and it works very well. I’d like to find an easy-to-use system like the one you nVidia did for Jetson models. Is there anything like this for x86?

DeepStream works on x86_64 Linux, and there are the TensorRT samples (same as on Jetson).

You might also want to see this thread about compiling jetson-inference for desktop: https://forums.developer.nvidia.com/t/how-to-build-jetson-inference-in-host-pc/53522/2?u=dusty_nv

Alternatively, due to the increased performance of desktop system, you may just be able to run it all in PyTorch.