Ignatov Andrey Apps

Loading...
AI Benchmark 3.0.0
Face Recognition, Image Classification, Image Enhancement... Isyour smartphone capable of running the latest Deep Neural Networksto perform these AI-based tasks? Does it have a dedicated AI Chip?Is it fast enough? Run AI Benchmark to comprehensively evaluateit's AI Performance! Current phone ranking:http://ai-benchmark.com/ranking.html AI Benchmark measures thespeed, accuracy and memory requirements for several key AI andComputer Vision algorithms. Among the tested solutions are ImageClassification and Face Recognition methods, Neural Networks usedfor Image Super-Resolution and Photo Enhancement, AI models playingAtari Games and performing Bokeh Simulation, as well as algorithmsused in autonomous driving systems. Visualization of thealgorithms’ output allows to assess their results graphically andto get to know the current state-of-the-art in various AI fields.In total, AI Benchmark consists of 21 tests and 11 sectionsprovided below: Section 1. Classification, MobileNet-V2 Section 2.Classification, Inception-V3 Section 3. Face Recognition,Inception-ResNet-V1 Section 4. Playing Atari Games, LSTM Section 5.Deblurring, SRCNN Section 6. Super-Resolution, VGG19 Section 7.Super-Resolution, SRGAN Section 8. Bokeh Simulation, U-Net Section9. Semantic Segmentation, ICNet Section 10. Image Enhancement, DPEDResNet Section 11. Memory limits, SRCNN A detailed description ofthe tests can be found here: http://ai-benchmark.com/tests.htmlNote: Hardware acceleration is supported on Android 9.0 and aboveon all mobile SoCs with AI accelerators, including QualcommSnapdragon, HiSilicon Kirin, Samsung Exynos and MediaTek Helio.