Neuralscope offers you benchmarking your AI solutions
1.   What Neuralscope can!
Since 2017, Mobile devices enable AI capability by adopting advance deep learning model and powerful chips. Choosing a device to perform huge computations and parametersaccess is a big challenge on power consumption and performance issues. Neuralscope benchmark App helps you to understand your mobile device performance.
2.   What Neuralscope has!
To evaluate abilities of deep learning mobile devices, AI system benchmarking and tuning lab (人工智慧系統檢測中心), National Chiao Tung University, Taiwan, announces a benchmark for deep learning neural network on mobile, named NeuralScope benchmark. This is based on Android NNAPI to test computational abilities of mobile devices. It is a multi-target benchmarking platform for evaluating how well a deep learning solution can accelerate versatile AI applications for different targets.
3.   What Neuralscope evaluates!
Our current test has a total of four categories, image classification, object detection, image segmentation and multi-task hybrid mode. And each of them have both floating & quantized test.
Image classification
The deep learning based neural networks are able to recognize object classes for one or more given input photos. They can recognize 1000 different object classes. There are four models, mobilenet-V1, mobilenet-V2, Resnet-50, and Inception-V3, in our benchmarking App. Individually, we provide one float model and one quantized model for each network.
Object detection
Now, you can perform object counting on your phone. The model we use is a combination of mobilenet, a light-weight classification model, and single shot multibox detector(SSD), an object detector does not resample pixels or feature maps for bounding box hypotheses, can detect 80 different object classes. It improves in speed for high-accuracy detection.
Image Segmentation
The task evaluates whether you can perform auto background removing for exchange scene on your phone. It can recognize 20 different object classes and segment the recognized object using different colors. The model is resnet-50 with atrous convolution layers embedded.