• documentation
main content

prototype deep learning networks on fpga -凯发k8网页登录

estimate performance of series networks. profile and retrieve inference results from target devices using matlab®

deep learning hdl toolbox™ provides classes to create objects to deploy series deep learning networks to target fpga and soc boards. before deploying deep learning networks onto target fpga and soc boards, leverage the methods to estimate the performance and resource utilization of the custom deep learning network. after you deploy the deep learning network, use matlab to retrieve the network prediction results from the target fpga board.

classes

configure deployment workflow for deep learning neural network
configure interface to target board for workflow deployment
create an object that retrieves intermediate layer results and validate deep learning network prediction accuracy

functions

retrieve intermediate layer results for deployed deep learning network
compile workflow object
deploy the specified neural network to the target fpga board
retrieve bitstream resource utilization
predictpredict responses by using deployed network
retrieve intermediate layers results for dlhdl.simulator object
retrieve prediction results for dlhdl.simulator object
validate ssh connection and deployed bitstream
release the connection to the target device

topics


  • accelerate the prototyping, deployment, design verification, and iteration of your custom deep learning network running on a fixed bitstream by using the dlhdl.workflow object.

  • libiio/ethernet connection based deep learning network deployment

    rapidly deploy deep learning networks to fpga boards using matlab.

  • profile inference run

    obtain performance parameters of an inference run performed for a pretrained series network and a specified target fpga board.


  • improve the performance of your deployed deep learning network by using the multiple frame support feature.

网站地图