Quantization and Pruning

Compress a deep neural network by performing quantization or pruning

Use Deep Learning Toolbox™ together with the Deep Learning Toolbox Model Quantization Library support package to reduce the memory footprint and computational requirements of a deep neural network by:

Quantizing the weights, biases, and activations of layers to reduced precision scaled integer data types. You can then generate C/C++, CUDA^®, or HDL code from this quantized network.
For C/C++ and CUDA code generation, the software generates code for a convolutional deep neural network by quantizing the weights, biases, and activations of the convolution layers to 8-bit scaled integer data types. The quantization is performed by providing the calibration result file produced by the calibrate function to the codegen (MATLAB Coder) command.
Code generation does not support quantized deep neural networks produced by the quantize function.
Pruning filters from convolution layers by using first-order Taylor approximation. You can then generate C/C++ or CUDA code from this pruned network.

Functions

expand all

Quantization

`dlquantizer`	Quantize a deep neural network to 8-bit scaled integer data types
`dlquantizationOptions`	Options for quantizing a trained deep neural network
`calibrate`	Simulate and collect ranges of a deep neural network
`quantize`	Quantize deep neural network
`validate`	Quantize and validate a deep neural network
`quantizationDetails`	Display quantization details for a neural network
`estimateNetworkMetrics`	Estimate network metrics for specific layers of a neural network
`equalizeLayers`	Equalize layer parameters of deep neural network

Pruning

`taylorPrunableNetwork`	Network that can be pruned by using first-order Taylor approximation
`forward`	Compute deep learning network output for training
`predict`	Compute deep learning network output for inference
`updatePrunables`	Remove filters from prunable layers based on importance scores
`updateScore`	Compute and accumulate Taylor-based importance scores for pruning
`dlnetwork`	Deep learning network for custom training loops

Apps

Deep Network Quantizer

Quantize a deep neural network to 8-bit scaled integer data types

Topics

Deep Learning Quantization

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.

Quantization for GPU Target

Generate INT8 Code for Deep Learning Networks (GPU Coder)
Quantize and generate code for a pretrained convolutional neural network.
Quantize Residual Network Trained for Image Classification and Generate CUDA Code
This example shows how to quantize the learnable parameters in the convolution layers of a deep learning neural network that has residual connections and has been trained for image classification with CIFAR-10 data.
Quantize Layers in Object Detectors and Generate CUDA Code
This example shows how to generate CUDA® code for an SSD vehicle detector and a YOLO v2 vehicle detector that performs inference computations in 8-bit integers for the convolutional layers.

Quantization for FPGA Target

Deploy INT8 Network to FPGA (Deep Learning HDL Toolbox)
Reduce the memory footprint of a deep neural network by quantizing the weights, biases, and activations of convolution layers to 8-bit scaled integer data types.
Classify Images on an FPGA Using a Quantized DAG Network (Deep Learning HDL Toolbox)
In this example, you use Deep Learning HDL Toolbox™ to deploy a quantized deep convolutional neural network and classify an image.
Classify Images on FPGA by Using Quantized GoogLeNet Network (Deep Learning HDL Toolbox)
This example show how to use the Deep Learning HDL Toolbox™ to deploy a quantized GoogleNet network to classify an image.

Quantization for CPU Target

Generate int8 Code for Deep Learning Networks (MATLAB Coder)
Quantize and generate code for a pretrained convolutional neural network.
Generate INT8 Code for Deep Learning Network on Raspberry Pi (MATLAB Coder)
Generate code for deep learning network that performs inference computations in 8-bit integers.

Pruning

Parameter Pruning and Quantization of Image Classification Network
Use parameter pruning and quantization to reduce network size.
Prune Image Classification Network Using Taylor Scores
This example shows how to reduce the size of a deep neural network using Taylor pruning.
Prune Filters in a Detection Network Using Taylor Scores
This example shows how to reduce network size and increase inference speed by pruning convolutional filters in a you only look once (YOLO) v3 object detection network.

Featured Examples

Parameter Pruning and Quantization of Image Classification Network

Use parameter pruning and quantization to reduce network size.

Open Live Script

Prune Image Classification Network Using Taylor Scores

Reduce the size of a deep neural network using Taylor pruning. By using the taylorPrunableNetwork function to remove convolution layer filters, you can reduce the overall network size and increase the inference speed.

Open Live Script

Prune Filters in a Detection Network Using Taylor Scores

Reduce network size and increase inference speed by pruning convolutional filters in a you only look once (YOLO) v3 object detection network.

Open Live Script