Comments (5)
I use the https://github.com/dusty-nv/jetson-scripts/blob/master/jetson_max_l4t.sh to max performance with tx1.
And it looks a little accelerate 6.7FPS up to 7.0FPS
from jetson-inference.
@FaceOP ,
I tried to get source from https://github.com/ross-abaco/jetson-inference to support USB camera, the FPS I got about 8 when running this command ./detectnet-camera ped-100. I think it should be about 20fps as this graph : https://devblogs.nvidia.com/parallelforall/wp-content/uploads/2016/09/Figure_3-1.png
Anyone have the better result ?
from jetson-inference.
@forever3000 @FaceOP Hi,
If you look carefully at the vertical axis of the image in the previous link, you will actually see that it is "frames per second per watt". The graph is about energy efficiency and not pure performance.
from jetson-inference.
Hi.
I succeeded in installation of OpenFrameworks to TX1.
http://takesan.hatenablog.com/entry/2016/12/19/214455
And detectnet(by jetson-inference) multiped-500 FPS is about 7.8~8 FPS and Camera FPS 60FPS by OF.
http://takesan.hatenablog.com/entry/2017/02/03/201108
I'm sorry, it is all Japanese.
By the way. 'jetson_clocks.sh' is not effective by this 'jetson-inference'. Why?
from jetson-inference.
from jetson-inference.
Related Issues (20)
- Web-RTC dash not have argument on app.py
- [TRT] 2: [utils.cpp::checkMemLimit::380] Error Code 2: Internal Error (Assertion upperBound != 0 failed. Unknown embedded device
- SyntaxError: future feature annotations is not defined HOT 2
- where is file named train_ssd.py ? HOT 2
- cudaEventElapsedTime device not ready (error 600) (hex 0x258) HOT 1
- [ WARN:0] global /opt/opencv/modules/videoio/src/cap_gstreamer.cpp (935)
- How to open csi camera in a docker container HOT 3
- How to use custom .onnx or .tflite model with inference ? HOT 1
- Problem with testing video viewer function HOT 7
- choose network precision as float32 HOT 1
- Questions about how to receive and use ROS1 image msg
- RuntimeError: CUDA error: too many resources requested for launch
- how to get networks/FlowNet-320x240/flownets.onnx HOT 2
- Action Recognition gets crashed after running for couple of seconds
- Fail to load vgg-16 for inferencing on Jetson Nano 4GB HOT 1
- detectnet with GMSL Camera
- Is there a way to manually EOS in python object? HOT 2
- How to save videos through videosource, instead of using output.render HOT 1
- MobileNetV3 constant dips in accuracy.
- unable to download ResNet18-Tagging-VOC/resnet18.onnx
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from jetson-inference.