Main Content

Deep Learning INT8 Quantization

Calibrate, validate, and deploy quantized pretrained series deep learning networks

Increase throughput, reduce resource utilization, and deploy larger networks onto smaller target boards by quantizing your deep learning networks.

After calibrating your pretrained series network by collecting instrumentation data, quantize your series network and validate the accuracy of your quantized network. Once the quantized network has been validated, generate code for and deploy the quantized network.

Functions

expand all

dlquantizationOptionsOptions for quantizing a trained deep neural network
dlquantizerQuantize a deep neural network to 8-bit scaled integer data types
calibrateSimulate and collect ranges of a deep neural network
validateQuantize and validate a deep neural network
dlhdl.WorkflowConfigure deployment workflow for deep learning neural network
dlhdl.TargetConfigure interface to target board for workflow deployment
dlhdl.SimulatorCreate an object that retrieves intermediate layer results and validate deep learning network prediction accuracy
compile Compile workflow object
deploy Deploy the specified neural network to the target FPGA board
predictRun inference on deployed network and profile speed of neural network deployed on specified target device
predictRetrieve prediction results for dlhdl.Simulator object
releaseRelease the connection to the target device
validateConnectionValidate SSH connection and deployed bitstream

Topics

Get Started

Quantization Workflow