The Xilinx Edge AI Platform provides comprehensive tools and models which utilize unique deep compression and hardware-accelerated Deep Learning technology.
The platform provides efficient, convenient and economical inference deployments for embedded-CPU-based FPGAs.
The Xilinx AI team consists of renowned researchers and experienced professionals known for their pioneering work in the field of deep learning.
DNNDK unleashes the productivity and efficiency of deploying AI inference on Xilinx Edge AI platforms.
DNNDK consists of:
With world-leading model compression technology, we can reduce model complexity by 5x to 50x with minimal accuracy impact. Deep Compression takes the performance of your AI inference to the next level.
Maps the AI model to high-efficient instruction set and data flow. Also performs sophisticate optimizations such as layer fusion, instruction scheduling, and reuses on-chip memory as much as possible.
The N2Cube runtime provides a lightweight set of tensor-based APIs enabling easy application development. It also provides efficient task scheduling, memory management and interrupt handling. The performance profiler allows programmers to perform in-depth analysis of the efficiency and utilization of your AI inference implementation.
The Deep-learning Processing Unit (DPU) is designed to be efficient, have low latency and be scalable for a wide range of edge AI applications. It supports the most commonly used network layers and operators, using hardware acceleration to take full advantage of the underlying Xilinx FPGA architecture and achieve the optimal tradeoff between latency, power and cost.
Xilinx Edge AI Platform supports a number of industry-standard frameworks, highlighted in the table below.
The Xilinx Edge AI Platform supports the AI/ML Models as shown below.
|General||Image classification||Resnet50, Inception v1, BN-inception, VGG16, SqueezeNet, MobilenetV2|
|Object Detection||MobilnetV2-SSD, SSD, YOLO v2, YOLO v3, Tiny YOLO v2, Tiny YOLO v3|
|Face||Face detection||SSD, Densebox|
|Landmark Localization||Coordinates Regression|
|Face recognition||ResNet + Triplet / A-softmax Loss|
|Face attributes recognition||Classification and regression|
|Pose Estimation||Coordinates Regression|
|Video Analytics||Object detection||SSD, RefineDet|
|Pedestrian Attributes Recognition||GoogleNet|
|Car Attributes Recognition||GoogleNet|
|Car Logo Recognition||Modified Densebox + GoogleNet|
|License Plate Detection||Modified DenseBox|
|License Plate Recognition||GoogleNet + Multi-task Learning|
|ADAS/AD||Object Detection||SSD, YOLOv2, YOLOv3|