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.
|Configure deployment workflow for deep learning neural network|
|Configure interface to target board for workflow deployment|
|Compile workflow object|
|Deploy the specified neural network to the target FPGA board|
|Estimate performance of specified deep learning network and bitstream for target device board|
|Run inference on deployed network and profile speed of neural network deployed on specified target device|
|Release the connection to the target device|
|Validate SSH connection and deployed bitstream|
Pretrained deep learning networks and network layers for which code can be generated by Deep Learning HDL Toolbox™.
Understand effects of quantization and how to visualize dynamic ranges of network convolution layers.
Products required for the quantization of deep learning networks.
Simulate your pretrained series network and collect the dynamic range of weights and biases.
Quantize and validate your pretrained series deep learning network.
Generate code and deploy your quantized pretrained series deep learning network.
Deploy a pretrained quantized series network.
Compare the accuracy between a pretrained series network and a quantized pretrained series network.