Comments (11)
Could this boost the performance?
I've tried mediapipe hands on gpu on android (s8) and they get about 20-25 fps but current hands implementation are very slow on pc. (i7 16 gb ram gti 960 ti)
from tf-lite-unity-sample.
Hi @TheBricktop, This is because the GPU delegate (a GPU acceleration feature of the TensorFlow Lite) is not supported on Window at the moment. I would like to support it eventually.
from tf-lite-unity-sample.
What ones should do to implement it? Recompile tf lite library?
from tf-lite-unity-sample.
It looks like to be not officially supported.
tensorflow/tensorflow#40325
from tf-lite-unity-sample.
So on android the performance would be higher?
from tf-lite-unity-sample.
Yes, if you are interested in using MediaPipe without the GPU delegate, please refer XNNPACK(this issue) or the integer quantized model
from tf-lite-unity-sample.
Would exporting tflite models to onnx and running in barracuda improve the performance?
from tf-lite-unity-sample.
Yes, if all ops are supported in Barracuda, could improve it. Please refer to the supported ops in Barracuda
from tf-lite-unity-sample.
Now, XNNPACK options are enabled in v2.4 libraries
from tf-lite-unity-sample.
@asus4 I suspect XNNPACK is not correctly enabled based on the following observations:
- Currently the CPU mode performance of
tf-lite-unity-sample
is closer to what I get from the official benchmark tool (https://www.tensorflow.org/lite/performance/measurement) withuse_xnnpack=false
. - From Tensorflow source code, I think
TfLiteXNNPackDelegateCreate
must be called in order for XNNPACK to be actually enabled. I don't see it being called anywhere intf-lite-unity-sample
. - When running the official benchmark tool with
use_xnnpack=true
, there will be a line in log that saysCreated TensorFlow Lite XNNPACK delegate for CPU
. It's missing whentf-lite-unity-sample
is run.
Would you like to take a look?
from tf-lite-unity-sample.
Thanks, @tonysung
I mistakenly thought it would be automatically enabled on the CPU mode. I will add XNNPack delegate.
from tf-lite-unity-sample.
Related Issues (20)
- Unable to support TensorFlow Lite Task Library model? HOT 5
- Accelerator compatibility issue on Android phones HOT 1
- Expose mediapipe config option "min_pose_detection_confidence" HOT 2
- face blendshape and geometry support HOT 4
- CameraTextureBackground doesn't support Built-in Render Pipeline HOT 4
- Custom model in SSD throws exception: TensorFlowLite operation failed HOT 3
- When the Graphics API is set to OpenGLES3, the ssd tracking does not work. HOT 2
- Fails TFLite Android build on CircleCI HOT 6
- deeplabv3_257_mv_gpu.tflite question HOT 2
- Having multiple tflite models deployed on same application HOT 5
- Better camera quality or a plugin instead of WebcamTexture HOT 1
- Facing Issue with Custom Model Integration HOT 2
- Map the landmarks on BlazePose Sample into a 3D avatar: eg Unity Chan? HOT 3
- Gpu Accelerator not working for linux x86_64. HOT 2
- undefined symbol errors on Xcode HOT 2
- This TensorFlow Lite and the one Xamarin - identical? HOT 1
- DllNotFoundException: libtensorflowlite_jni HOT 2
- Audio classification will produce different results on different runs HOT 9
- Blazepose runs very slowly on mobile HOT 1
- using static image instead of WebCamTexture on BlazePose HOT 2
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 tf-lite-unity-sample.