dlhdl.Workflow class

Package: dlhdl

Configure deployment workflow for deep learning neural network

Description

Use the dlhdl.Workflow object to set options for compiling and deploying your deep learning network to a target FPGA. You create an object of the dlhdl.Workflow class for the specified deep learning network and FPGA bitstream. Use the object to:

Compile the deep learning network.
Estimate the speed and throughput of your network on the specified FPGA device.
Compile and deploy the neural network onto the FPGA.
Predict the class of input images.
Profile the results for the specified network and the FPGA.

Creation

dlhdl.Workflow creates a workflow configuration object for you to specify the workflow to deploy your trained series network.

dlhdl.Workflow (Name,Value) creates a workflow configuration object for you to specify the workflow to deploy your trained deep learning network, with additional options specified by one or more name-value pair arguments.

Properties

Bitstream — Name of the FPGA bitstream '' (default) | character vector

Name of the FPGA bitstream, specified as a character vector. Make sure that the bitstream name matches the data type and the FPGA board that you are targeting. For a list of provided bitstream names, see Use Deep Learning on FPGA Bitstreams.

Example: 'Bitstream', 'arria10soc_single' specifies that you want to deploy the trained network with single data types to an Arria10 SoC board.

Example:'Bitstream','myfile.bit' specifies that you want to deploy the trained network using your custom bitstream file myfile.bit which is in your current working directory.

Example:'Bitstream','C:\myfolder\myfile.bit' specifies that you want to deploy the trained network using your custom bitstream file myfile.bit that is located in the folder 'C:\myFolder'.

Network — Name of the pretrained deep learning network that you want to import or the name of the quantized network object
' ' (default)

Deep learning network name specified as a variable

Example: 'network', snet creates a workflow object for the saved pretrained network, snet. To specify snet, you can import any of the existing supported pretrained networks or use transfer learning to adapt the network to your problem. For information on supported networks, see Supported Pretrained Networks.

Example: 'network', dlquantizeObj creates a workflow object for the quantized network object, dlquantizeObj. To specify dlquantizeObj, you can import any of the supported existing pretrained networks and create an object using the dlquantizer class. For information on supported networks, see Supported Pretrained Networks.

Assign VGG-19 to snet:

snet = vgg19;

`'ProcessorConfig'` — Optional arguments when estimating workflow object without a bitstream
`ProcessorConfig` (default) | `dlhdl.ProcessorConfig`

Custom processor configuration object specified as dlhdl.ProcessorConfig object

Example: 'ProcessorConfig',hPC

hPC = dlhdl.ProcessorConfig()
hW = dlhdl.Workflow('network', alexnet,'ProcessorConfig',hPC);

`'Target'` — `dlhdl.Target` object to deploy network and bitstream to the target device
`hTarget`

Target object specified as dlhdl.Target object

Example: 'Target',hTarget

hTarget = dlhdl.Target('Intel','Interface','JTAG')
hW = dlhdl.Workflow('network', snet,'Bitstream','arria10soc_single','Target',hTarget);

Examples

Create Workflow Object by using Property Name Value Pairs

snet = vgg19;
hW = dlhdl.Workflow('Network',snet,'Bitstream','arria10soc_single', 'Target', hTarget');

Create Workflow Object Using Custom Bitstream

snet = vgg19;
hW = dlhdl.Workflow('Network',snet,'Bitstream','myfile.bit', 'Target', hTarget);

Create Workflow Object with Quantized Network Object

snet = getLogoNetwork();
dlquantObj = dlquantizer(snet,'ExecutionEnvironment','FPGA');
Image = imageDatastore('heineken.png','Labels','Heineken');
dlquantizeObj.calibrate(Image);
hTarget = dlhdl.Target('Xilinx','Interface','Ethernet');
hW = dlhdl.Workflow('Network',dlquantizeObj,'Bitstream','zcu102_int8','Target',hTarget);

Matlabsolutions.com provides guaranteed satisfaction with a commitment to complete the work within time. Combined with our meticulous work ethics and extensive domain experience, We are the ideal partner for all your homework/assignment needs. We pledge to provide 24*7 support to dissolve all your academic doubts. We are composed of 300+ esteemed Matlab and other experts who have been empanelled after extensive research and quality check.

Matlabsolutions.com provides undivided attention to each Matlab assignment order with a methodical approach to solution. Our network span is not restricted to US, UK and Australia rather extends to countries like Singapore, Canada and UAE. Our Matlab assignment help services include Image Processing Assignments, Electrical Engineering Assignments, Matlab homework help, Matlab Research Paper help, Matlab Simulink help. Get your work done at the best price in industry.