DEEPX新款M1NPU提供灵活性准确性效率和性能

DEEPX’s New M1 NPU Delivers Flexibility, Accuracy, Efficiencyand Performance Jay KimExecutive Vice PresidentDEEPXDisruptive Innovation “IT’S REAL”2© 2023 DEEPXDX-M1: 133 FPS (Yolov7)mAP: 50.900V100: 229 FPS (Yolov7)mAP: 51.0Batch Size =1Batch Size =1DEEPX’s Key Differentiators© 2023 DEEPX3DEEPX’s Key Differentiators –1. Flexibility 4© 2023 DEEPX✓Latest: Latest DNN algorithms (SOTA)-EfficientNet, YoloX, YoloV7, PIDNet…✓Wide Range: Various kinds of algorithms-Classification, object detection, segmentation,pose estimation,anomalydetection…✓Complex Algorithms: Normally too complex for edge NPUs -DeepX NPU can run PIDNet, SFA3D(Sensor Fusion)→ Customers can use our NPU longer and wider.Evidence #1: SOTA Support (Object Detection)5© 2023 DEEPXDEEPX’s Key Differentiators –2. Accuracy ✓Use int 8-bit instead of 32-bit floating point operations-Expect accuracy drop comparing to GPU ✓Almost the same accuracy as a GPU can get -Normally same or less than 1% accuracy drop expected✓Wow factor: B