• documentation
main content

time series and sequence data networks -凯发k8网页登录

deploy networks trained for time series classification, regression, and forecasting tasks to target fpga and soc boards

you can train and deploy networks to do time series classification, regression, and forecasting tasks by using long short-term memory (lstm) networks. an lstm is a type of recurrent neural network (rnn) that can learn long-term dependencies between time steps of sequence data. learn about:

  • support for lstm networks.

  • how deep learning hdl toolbox™ compiles the lstm layer in a network.

  • how to deploy lstm networks to target fpga and soc boards, then use deep learning hdl toolbox and matlab to retrieve the prediction results from the network.

classes

configure deployment workflow for deep learning neural network
configure interface to target board for workflow deployment

functions

release the connection to the target device
validate ssh connection and deployed bitstream
retrieve intermediate layer results for deployed deep learning network
compile workflow object
deploy the specified neural network to the target fpga board
predictpredict responses by using deployed network
predict responses by using a trained and deployed recurrent neural network and update the deployed network state
reset state parameters of deployed neural network

topics


  • learn about deep learning hdl toolbox support for long short-term memory (lstm) networks.


  • understand how the compile method interprets an lstm layer.


  • understand how deep learning hdl toolbox interprets the gru layer.


  • 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.

网站地图