Deep Learning INT8 Quantization
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.
Quantization and Validation
|Options for quantizing a trained deep neural network (Since R2020a)|
|Quantize a deep neural network to 8-bit scaled integer data types (Since R2020a)|
|Simulate and collect ranges of a deep neural network (Since R2020a)|
|Quantize and validate a deep neural network (Since R2020a)|
|Quantize deep neural network (Since R2022a)|
Code Generation and Deployment
|Configure deployment workflow for deep learning neural network (Since R2020b)|
|Configure interface to target board for workflow deployment (Since R2020b)|
|Create an object that retrieves intermediate layer results and validate deep learning network prediction accuracy (Since R2021b)|
|Compile workflow object (Since R2020b)|
|Deploy the specified neural network to the target FPGA board (Since R2020b)|
|Predict responses by using deployed network (Since R2020b)|
|Retrieve prediction results for |
|Release the connection to the target device (Since R2020b)|
|Validate SSH connection and deployed bitstream (Since R2020b)|
- Supported Networks, Layers, Boards, and Tools
Pretrained deep learning networks and network layers for which code can be generated by Deep Learning HDL Toolbox™.
- Quantization of Deep Neural Networks
Understand effects of quantization and how to visualize dynamic ranges of network convolution layers.
- Quantization Workflow Prerequisites
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.
- Code Generation and Deployment
Generate code and deploy your quantized pretrained series deep learning network.