GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → freedomtan → glDelegateBenchmark

freedomtan / glDelegateBenchmark

Licence: BSD-3-Clause license
quick and dirty benchmark for TFLite gles delegate on iOS

Programming Languages

Objective-C++
1391 projects
objective c
16641 projects - #2 most used programming language
ruby
36898 projects - #4 most used programming language

Labels

iosbenchmarktensorflowgpumobilenetposenettensorflow-litedeeplabv3tflitemobilenetv2-ssdlitetflite-delegatetflite-gpu-delegate

Projects that are alternatives of or similar to glDelegateBenchmark

glDelegateBench
quick and dirty inference time benchmark for TFLite gles delegate
Stars: ✭ 17 (+30.77%)
Mutual labels:  benchmark, tensorflow-lite, tflite, tflite-delegate, tflite-gpu-delegate
E2E-tfKeras-TFLite-Android
End to end training MNIST image classifier with tf.Keras, convert to TFLite and deploy to Android
Stars: ✭ 17 (+30.77%)
Mutual labels:  tensorflow-lite, tflite
Selfie2Anime-with-TFLite
How to create Selfie2Anime from tflite model to Android.
Stars: ✭ 70 (+438.46%)
Mutual labels:  tensorflow-lite, tflite
Tensorflow-lite-kotlin-samples
📌This repo contains the kotlin implementation of TensorflowLite Example Android Apps🚀
Stars: ✭ 17 (+30.77%)
Mutual labels:  tensorflow-lite, tflite
MobileNet-SSD-windows
No description or website provided.
Stars: ✭ 91 (+600%)
Mutual labels:  mobilenet, mobilenetv2-ssdlite
YOLOv5-Lite
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
Stars: ✭ 1,230 (+9361.54%)
Mutual labels:  mobilenet, tflite
TFLite-Mobile-Generic-Object-Localizer
Python TFLite scripts for detecting objects of any class in an image without knowing their label.
Stars: ✭ 42 (+223.08%)
Mutual labels:  tensorflow-lite, tflite
LightNet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 710 (+5361.54%)
Mutual labels:  mobilenet, deeplabv3
tflite-vx-delegate
Tensorflow Lite external delegate based on TIM-VX
Stars: ✭ 28 (+115.38%)
Mutual labels:  tflite, tflite-delegate
backscrub
Virtual Video Device for Background Replacement with Deep Semantic Segmentation
Stars: ✭ 691 (+5215.38%)
Mutual labels:  deeplabv3, tflite
android tflite
GPU Accelerated TensorFlow Lite applications on Android NDK. Higher accuracy face detection, Age and gender estimation, Human pose estimation, Artistic style transfer
Stars: ✭ 105 (+707.69%)
Mutual labels:  tensorflow-lite, tflite
embeddings
Embeddings: State-of-the-art Text Representations for Natural Language Processing tasks, an initial version of library focus on the Polish Language
Stars: ✭ 27 (+107.69%)
Mutual labels:  benchmark
Python-Complementary-Languages
Just a small test to see which language is better for extending python when using lists of lists
Stars: ✭ 32 (+146.15%)
Mutual labels:  benchmark
MDBenchmark
Quickly generate, start and analyze benchmarks for molecular dynamics simulations.
Stars: ✭ 64 (+392.31%)
Mutual labels:  benchmark
Mobile Image-Video Enhancement
Sensifai image and video enhancement module on mobiles
Stars: ✭ 39 (+200%)
Mutual labels:  tflite
gpumembench
A GPU benchmark suite for assessing on-chip GPU memory bandwidth
Stars: ✭ 62 (+376.92%)
Mutual labels:  benchmark
benchmarkjs-pretty
Tiny wrapper around benchmarkjs with a nicer api
Stars: ✭ 20 (+53.85%)
Mutual labels:  benchmark
quic vs tcp
A Survey and Benchmark of QUIC
Stars: ✭ 41 (+215.38%)
Mutual labels:  benchmark
graphql-bench
A super simple tool to benchmark GraphQL queries
Stars: ✭ 222 (+1607.69%)
Mutual labels:  benchmark
php-benchmarks
It is a collection of php benchmarks
Stars: ✭ 38 (+192.31%)
Mutual labels:  benchmark
View All Similar Projects ➔

glDelegateBenchmark

quick and dirty inference time benchmark for TFLite gles delegate on iOS

The TensorFlow team announced TFLite GPU delegate and published related docs [2][3] in Jan 2019. But except Mobilenet V1 classifier, there is no publicly available app to evaluate it, so I wrote a quick and dirty app to evaluate other models.

For the 4 public models mentioned in [1], I got the following numbers on iPhone 7.

model name CPU 1 thread (ms) CPU 2 threads (ms) GPU (ms)
Mobilenet V1 1.0 224 40.62 29.67 15.97
PoseNet 51.68 35.38 19.44
DeepLab V3 (257x257) 62.02 46.08 25.63
Mobilnet V2 SSD COCO 69.97 56.61 29.78

As far as I can tell, CPU numbers are larger than I expect, because we cannot control clock frequncies of CPUs.

On iPhone 11 Pro, I got

model name CPU 1 thread (ms) CPU 2 threads (ms) GPU (ms) CoreML Delegate (ms) [4]
Mobilenet V1 1.0 224 26.54 18.21 10.91 2.03
PoseNet 34.14 23.62 16.75 3.34
DeepLab V3 (257x257) 39.65 29.87 20.43 9.10
Mobilnet V2 SSD COCO 44.94 34.05 19.73 11.54

Check https://github.com/freedomtan/glDelegateBench/ for Android code

[1] https://medium.com/tensorflow/tensorflow-lite-now-faster-with-mobile-gpus-developer-preview-e15797e6dee7

[2] https://www.tensorflow.org/lite/performance/gpu

[3] https://www.tensorflow.org/lite/performance/gpu_advanced

[4] https://www.tensorflow.org/lite/performance/coreml_delegate

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].