Comments (9)
if I run the L2Norm with the FloatArrays that I get from the Xiaomi, Samsung can do the calculation correctly.
from facerecognition_with_facenet_android.
This is because of different device configurations. Probably switching off the GpuDelegate
and XNNPack
might help.
In the FaceNetModel.kt
class, you'll see these lines,
init {
// Initialize TFLiteInterpreter
val interpreterOptions = Interpreter.Options().apply {
// Add the GPU Delegate if supported.
// See -> https://www.tensorflow.org/lite/performance/gpu#android
if ( CompatibilityList().isDelegateSupportedOnThisDevice ) {
addDelegate( GpuDelegate( CompatibilityList().bestOptionsForThisDevice ))
}
else {
// Number of threads for computation
setNumThreads( 4 )
}
setUseXNNPACK( true )
}
interpreter = Interpreter(FileUtil.loadMappedFile(context, model.assetsFilename ) , interpreterOptions )
Logger.log("Using ${model.name} model.")
}
Replace these lines with,
init {
// Initialize TFLiteInterpreter
val interpreterOptions = Interpreter.Options().apply {
setNumThreads( 4 )
}
interpreter = Interpreter(FileUtil.loadMappedFile(context, model.assetsFilename ) , interpreterOptions )
Logger.log("Using ${model.name} model.")
}
from facerecognition_with_facenet_android.
@emreakcan Could you resolve the error by removing GpuDelegate
?
from facerecognition_with_facenet_android.
HI @shubham0204,
I'm also facing the same issue with face recognition. Initially, it generated multiple results for the same face. But now after removing the GPUDelegate and XNNPack, for all the faces it is giving me the same result as unknown.
from facerecognition_with_facenet_android.
@DineshIT can you send me some more details of the Samsung A21 device on which you're testing the app? I need these details specifically:
- Android OS Version
- GPU Renderer
- Supported ABIs
- CPU architecture
You can get these details by installing the Device Info app on the device.
from facerecognition_with_facenet_android.
from facerecognition_with_facenet_android.
Hi @shubham0204
I have worked on this issue and fixed it by adding the properties in the interpreter class object.
Please check my commit in the repo and merge it to handle this issue.
Hi @emreakcan
You can make the mentioned changes in your FaceNetModel Class and verify whether this issue got fixed at your end. If you got success please share with us.
from facerecognition_with_facenet_android.
@DineshIT Can you open a PR in this repo, so that I can review the changes?
from facerecognition_with_facenet_android.
PR has been created
from facerecognition_with_facenet_android.
Related Issues (20)
- Error in FrameAnalyser.kt : Cannot copy to a TensorFlowLite tensor (input_1) with 307200 bytes from a Java Buffer with 150528 bytes HOT 4
- [Error] : Getting facelist.size as 0 in FrameAnalyser.kt HOT 12
- l2 Norm not working as expected. HOT 13
- I am getting same name for every image in the frame HOT 6
- [request] write detection log to a file
- [issue] Always assign a face even if the image does not exist. HOT 2
- How to train the facenet model HOT 2
- Device orientation problem HOT 3
- bounding box overlay not showing properly. HOT 1
- Internal error: Failed to apply delegate with GpuDelegate HOT 3
- App is hanging with 300 Images HOT 3
- TfLiteGpuDelegate Invoke: GpuDelegate must run on the same thread HOT 3
- Multiple facial recognition in a single frameis not detecting properly HOT 2
- Access denied finding property "ro.mediatek.platform"! HOT 6
- Works on phone but not on tablet HOT 1
- How to improve the accuracy of facenet ?
- Can the source of the photo not be from storage but from a photo link? HOT 2
- landscape orientation HOT 2
- Application of tflite models and how to convert them. 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 facerecognition_with_facenet_android.