深度学习工具箱参考指南

需积分: 9 179 浏览量更新于2024-07-15 收藏 12.15MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

资源详情

资源推荐

For example, open Deep Network Designer with a pretrained SqueezeNet network.

net = squeezenet;

deepNetworkDesigner(net);

If Deep Network Designer is already open, deepNetworkDesigner(net) brings focus to the app

and prompts you to add to or replace any existing network.

Tips

To train multiple networks and compare the results, try Experiment Manager.

See Also

Functions

Experiment Manager | analyzeNetwork | trainNetwork | trainingOptions

Topics

“Transfer Learning with Deep Network Designer”

“Build Networks with Deep Network Designer”

“Import Data into Deep Network Designer”

“Create Simple Sequence Classication Network Using Deep Network Designer”

“Create Simple Semantic Segmentation Network in Deep Network Designer”

“Image-to-Image Regression in Deep Network Designer”

“Import Custom Layer into Deep Network Designer”

“Generate MATLAB Code from Deep Network Designer”

“List of Deep Learning Layers”

Introduced in R2018b

1 Deep Learning Functions

1-10

Open the Deep Network Quantizer App

• MATLAB command prompt: Enter deepNetworkQuantizer.

Examples

Quantize a Network

To explore the behavior of a neural network with quantized convolution layers, use the Deep

Network Quantizer app. This example quantizes the learnable parameters of the convolution layers

of the squeezenet neural network after retraining the network to classify new images according to

the “Train Deep Learning Network to Classify New Images” example.

Load the network to quantize into the base workspace.

net

net =

DAGNetwork with properties:

Layers: [68x1 nnet.cnn.layer.Layer]

Connections: [75x2 table]

InputNames: {'data'}

OutputNames: {'new_classoutput'}

Dene calibration and validation data.

The app uses calibration data to exercise the network and collect the dynamic ranges of the weights

and biases in the convolution and fully connected layers of the network and the dynamic ranges of the

activations in all layers of the network. For the best quantization results, the calibration data must be

representative of inputs to the network.

The app uses the validation data to test the network after quantization to understand the eects of

the limited range and precision of the quantized learnable parameters of the convolution layers in the

network.

In this example, use the images in the MerchData data set. Dene an augmentedImageDatastore

object to resize the data for the network. Then, split the data into calibration and validation data sets.

unzip('MerchData.zip');

imds = imageDatastore('MerchData', ...

'IncludeSubfolders',true, ...

'LabelSource','foldernames');

[calData, valData] = splitEachLabel(imds, 0.7, 'randomized');

aug_calData = augmentedImageDatastore([227 227], calData);

aug_valData = augmentedImageDatastore([227 227], valData);

At the MATLAB command prompt, open the app.

deepNetworkQuantizer

In the app, click the New button. The app veries your execution environment. To use the Deep

Network Quantizer app, you must have a GPU execution environment. If there is no GPU available,

this step produces an error.

Deep Learning Functions

1-12

剩余1657页未读，继续阅读

curemoon

粉丝: 17
资源: 8

深度学习工具箱参考指南

Deep Learning Toolbox Getting Started Guide_R2020b.pdf

Deep Learning Toolboxs

深度学习工具包 DeepLearningToolbox

怎么安装deep learning toolbox

deep learning toolbox 安装

下载deep learning toolbox

deep learning toolbox 下载

安装Deep Learning Toolbox

matlab中Deep Learning Toolbox Model for ResNet-50 Network和Deep Learning Toolbox Model for Inception-v3 Network怎么安装

2022deep learning toolbox安装

Deep Learning Toolbox怎么安装

MATLAB DEEP LEARNING TOOLBOX怎么下载

deep learning toolbox model quantization library 下载

没有许可证怎么安装Deep Learning Toolbox Model for AlexNet Network

怎么安装Deep Learning Toolbox

matlab软件怎么安装Reinforcement Learning Toolbox和Deep Learning Toolbox

deeplearning toolbox 下载方式

deep learning toolbox2022b安装包

如何加载Deep Learning Toolbox库

deep learning toolbox安装

最新资源