Code Generation and Deployment
To generated code for and deploy your quantized deep learning network, create an object
of class dlhdl.Workflow. Use this object to accomplish tasks such as:
Compile and deploy the quantized deep learning network on a target FPGA or SoC board by using the
deployfunction.Estimate the speed of the quantized deep learning network in terms of number of frames per second by using the
estimatefunction.Execute the deployed quantized deep learning network and predict the classification of input images by using the
predictfunction.Calculate the speed and profile of the deployed quantized deep learning network by using the
predictfunction. Set theProfileparameter toon.
This figure illustrates the workflow to deploy your quantized deep learning network to the FPGA boards.
See Also
dlhdl.Target | dlhdl.Workflow | dlquantizer