A LibTorch inference implementation of the yolov5 object detection algorithm. Both GPU and CPU are supported.
- Ubuntu 16.04
- CUDA 10.2
- OpenCV 3.4.12
- LibTorch 1.6.0
Please refer to the official document here: ultralytics/yolov5#251
Mandatory Update: developer needs to modify following code from the original export.py in yolov5
# line 29
model.model[-1].export = False
Add GPU support: Note that the current export script in yolov5 uses CPU by default, the "export.py" needs to be modified as following to support GPU:
# line 28
img = torch.zeros((opt.batch_size, 3, *opt.img_size)).to(device='cuda')
# line 31
model = attempt_load(opt.weights, map_location=torch.device('cuda'))
Export a trained yolov5 model:
cd yolov5
export PYTHONPATH="$PWD" # add path
python models/export.py --weights yolov5s.pt --img 640 --batch 1 # export
$ cd /path/to/libtorch-yolo5
$ wget https://download.pytorch.org/libtorch/cu102/libtorch-cxx11-abi-shared-with-deps-1.6.0.zip
$ unzip libtorch-cxx11-abi-shared-with-deps-1.6.0.zip
$ mkdir build && cd build
$ cmake .. && make
To run inference on examples in the ./images
folder:
# CPU
$ ./libtorch-yolov5 --source ../images/bus.jpg --weights ../weights/yolov5s.torchscript.pt --view-img
# GPU
$ ./libtorch-yolov5 --source ../images/bus.jpg --weights ../weights/yolov5s.torchscript.pt --gpu --view-img
# Profiling
$ CUDA_LAUNCH_BLOCKING=1 ./libtorch-yolov5 --source ../images/bus.jpg --weights ../weights/yolov5s.torchscript.pt --gpu --view-img
- terminate called after throwing an instance of 'c10::Error' what(): isTuple() INTERNAL ASSERT FAILED
- Make sure "model.model[-1].export = False" when running export script.
-
Why the first "inference takes" so long from the log?
-
The first inference is slower as well due to the initial optimization that the JIT (Just-in-time compilation) is doing on your code. This is similar to "warm up" in other JIT compilers. Typically, production services will warm up a model using representative inputs before marking it as available.
-
It may take longer time for the first cycle. The yolov5 python version run the inference once with an empty image before the actual detection pipeline. User can modify the code to process the same image multiple times or process a video to get the valid processing time.
-
- https://github.com/ultralytics/yolov5
- Question about the code in non_max_suppression
- https://github.com/walktree/libtorch-yolov3
- https://pytorch.org/cppdocs/index.html
- https://github.com/pytorch/vision
- PyTorch.org - CUDA SEMANTICS
- PyTorch.org - add synchronization points
- PyTorch - why first inference is slower
libtorch-yolov5's People
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.