[TF Lite] TensorFlow Lite with OpenGL ES

TensorFlow Lite

一、源码

Ref: https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite

 

二、性能实测

Ref: TensorFlow Lite GPU 代理，40 ms，即是22fps。

Ref: TensorFlow Lite 2019 Roadmap，OpenCL and Vulkan support on Android.

 

三、性能对比

Ref: https://www.tensorflow.org/lite/models/object_detection/overview

 

Android手机

模型名称	设备	平均推理时间
Mobilenet_1.0_224(float)	Pixel 2	123.3 ms
	Pixel XL	113.3 ms
Mobilenet_1.0_224 (quant)	Pixel 2	65.4 ms
	Pixel XL	74.6 ms
NASNet mobile	Pixel 2	273.8 ms
	Pixel XL	210.8 ms
SqueezeNet	Pixel 2	234.0 ms
	Pixel XL	158.0 ms
Inception_ResNet_V2	Pixel 2	2846.0 ms
	Pixel XL	1973.0 ms
Inception_V4	Pixel 2	3180.0 ms
	Pixel XL	2262.0 ms

 

iPhone手机

模型名称	设备	平均推理时间
Mobilenet_1.0_224(float)	iPhone 8	32.2 ms
Mobilenet_1.0_224 (quant)	iPhone 8	24.4 ms
NASNet mobile	iPhone 8	60.3 ms
SqueezeNet	iPhone 8	44.3
Inception_ResNet_V2	iPhone 8	562.4 ms
Inception_V4	iPhone 8	661.0 ms

 

 

2019年的旗舰手机

Performance benchmark numbers are generated with the tool described here.

Model Name	Model size	Device	GPU	CPU
COCO SSD MobileNet v1	27 Mb	Pixel 3 (Android 10)	22ms	46ms*
		Pixel 4 (Android 10)	20ms	29ms*
		iPhone XS (iOS 12.4.1)	7.6ms	11ms**

* 4 threads used.

** 2 threads used on iPhone for the best performance result.

 

 

 

TensorFlow Lite GPU delegate

一、Demo App Tutorials

Ref: https://www.tensorflow.org/lite/performance/gpu 

 

 

 

 

 

 

 

 /* implement */