ドキュメンテーション

最新のリリースでは、このページがまだ翻訳されていません。 このページの最新版は英語でご覧になれます。

深層学習の応用

コンピューター ビジョン、画像処理、自動運転、および信号による深層学習のワークフローの拡張

MATLAB® で深層学習のワークフローを拡張し、コンピューター ビジョン、画像処理、自動運転、信号などに応用します。たとえば、オブジェクト検出器の学習やセマンティック セグメンテーションを行って、イメージの各ピクセルを分類できます。

トピック

コンピューター ビジョン

深層学習を使用したセマンティック セグメンテーション

この例では、深層学習を使用してセマンティック セグメンテーション ネットワークの学習を行う方法を説明します。

Semantic Segmentation of Multispectral Images Using Deep Learning

This example shows how to train a U-Net convolutional neural network to perform semantic segmentation of a multispectral image with seven channels: three color channels, three near-infrared channels, and a mask.

Semantic Segmentation Using Dilated Convolutions

This example shows how to train a semantic segmentation network using dilated convolutions.

Define Custom Pixel Classification Layer with Dice Loss

This example shows how to define and create a custom pixel classification layer that uses Dice loss.

Object Detection Using Deep Learning

This example shows how to train an object detector using deep learning and R-CNN (Regions with Convolutional Neural Networks).

Object Detection Using Faster R-CNN Deep Learning

This example shows how to train an object detector using a deep learning technique named Faster R-CNN (Regions with Convolutional Neural Networks).

画像処理

Remove Noise from Color Image Using Pretrained Neural Network

This example shows how to remove Gaussian noise from an RGB image. Split the image into separate color channels, then denoise each channel using a pretrained denoising neural network, DnCNN.

Single Image Super-Resolution Using Deep Learning

This example shows how to train a Very-Deep Super-Resolution (VDSR) neural network, then use a VDSR network to estimate a high-resolution image from a single low-resolution image.

JPEG Image Deblocking Using Deep Learning

This example shows how to train a denoising convolutional neural network (DnCNN), then use the network to reduce JPEG compression artifacts in an image.

Image Processing Operator Approximation Using Deep Learning

This example shows how to train a multiscale context aggregation network (CAN) that is used to approximate an image filtering operation.

自動運転

Train a Deep Learning Vehicle Detector

This example shows how to train a vision-based vehicle detector using deep learning.

Create Occupancy Grid Using Monocular Camera and Semantic Segmentation

This example shows how to estimate free space and create an occupancy grid using semantic segmentation and deep learning. You then use this occupancy grid to create a vehicle costmap.

信号

Classify ECG Signals Using Long Short-Term Memory Networks

This example shows how to classify heartbeat electrocardiogram (ECG) data from the PhysioNet 2017 Challenge using deep learning and signal processing. In particular, the example uses Long Short-Term Memory (LSTM) networks and time-frequency analysis.

Classify Time Series Using Wavelet Analysis and Deep Learning

This example shows how to classify human electrocardiogram (ECG) signals using the continuous wavelet transform (CWT) and a deep convolutional neural network (CNN).

深層学習を使用した音声コマンド認識

この例では、オーディオに存在する音声コマンドを検出するシンプルな深層学習モデルに学習させる方法を説明します。

Denoise Speech Using Deep Learning Networks

This example shows how to denoise speech signals using deep learning networks. The example compares two types of networks applied to the same task: fully connected, and convolutional.

Classify Gender Using Long Short-Term Memory Networks

This example shows how to classify the gender of a speaker using deep learning. In particular, the example uses a Bidirectional Long Short-Term Memory (BiLSTM) network and Gammatone Cepstral Coefficients (gtcc), pitch, harmonic ratio, and several spectral shape descriptors.

注目の例