Comments (4)
Hi @vizero1, the first inference is expected to take a long time because TensorRT will be building the engines.
In DLR 1.2 we added a feature to cache the engine to disk after it has been built so that next time you load the model it doesn’t need to be built again and the first inference will be fast. You can read about it here https://neo-ai-dlr.readthedocs.io/en/latest/tensorrt.html#caching-tensorrt-engines
Please see this page for more details on TRT options for DLR: https://neo-ai-dlr.readthedocs.io/en/latest/tensorrt.html
from neo-ai-dlr.
@trevor-m thanks for the fast reply. I will try it out with the caching functionality but one thing is still not clear for me.
Why is there such a big difference between the different Jetpack versions? Is it due to the TRT versions?
Jetpack 4.3 with TRT 6 takes 5 minutes while Jetpack 4.4 with TRT 7 takes around 2 minutes?
from neo-ai-dlr.
Yes it is due to the TensorRT version. JetPack 4.4 uses TRT 7.1 which optimized engine build time. See “Builder layer timing cache” on this page https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-7.html#rel_7-1-3
from neo-ai-dlr.
@trevor-m thanks.
from neo-ai-dlr.
Related Issues (20)
- dlr 1.7.0 pip wheel for x86_64 target HOT 1
- importing dlr prodcuing error
- CudaLaunchError : CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES
- "make install" is not supported (CMAKE_INSTALL_PREFIX) HOT 1
- Neo, XGBoost, and ONNX
- CUDA driver version is insufficient for CUDA runtime version HOT 1
- Failed to initialize Lambda runtime due to exception: No module named 'dlr' HOT 1
- Unhashable type: dict
- How to get accuracy using dlr runtime??
- SetDLROutputTensorZeroCopy
- Can we add treelite specific backend? HOT 1
- DLR Building on Jetson Device Throws unhandled errors HOT 2
- Jetson Xavier Inference Crashes on TRT8 HOT 3
- A question about GIL
- I am Building on a BeagleBone AI-64 and Receiving the Below Errors... HOT 3
- Cannot disable Phone Home from read-only filesystem
- Planned support for Neuron runtime?
- Not working with jetpack 4.6 HOT 1
- Segmentation fault (core dumped) on the Jetson Nano
- Jetpackt 4.6 support HOT 1
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 neo-ai-dlr.