使用深度学习进行图像处理 -凯发k8网页登录

使用深度神经网络执行图像处理任务，例如去除图像噪声和执行图像到图像的转换（需要 deep learning toolbox™）

深度学习使用神经网络直接从数据中学习有用的特征表示。例如，您可以使用预训练神经网络来识别和去除图像中的噪声等项。

函数

	transform batches to augment image data
	datastore for use with blocks from `blockedimage` objects
	denoising image datastore
	图像数据的数据存储
	datastore for extracting random 2-d or 3-d random patches from images or pixel label images
	变换数据存储
	合并来自多个数据存储的数据

	randomly alter color of pixels
	randomly select rectangular region in image
	create randomized cuboidal cropping window
	create rectangular center cropping window
	create cuboidal center cropping window
	spatial extents of 2-d rectangular region
	spatial extents of 3-d cuboidal region
	create randomized 2-d affine transformation
	create randomized 3-d affine transformation
	create output view for warping images
	remove image pixels within rectangular region of interest

	2-d resize layer
	3-d resize layer
	resize spatial dimensions of `dlarray` object
	depth to space layer
	space to depth layer
	rearrange `dlarray` data from depth dimension into spatial blocks
	rearrange spatial blocks of `dlarray` data along depth dimension

	create encoder-decoder network
	create network with repeating block structure
	create encoder network from pretrained network
	create cyclegan generator network for image-to-image translation
	create patchgan discriminator network
	create pix2pixhd global generator network
	add local enhancer network to pix2pixhd generator network
	create unsupervised image-to-image translation (unit) generator network
	perform inference using unsupervised image-to-image translation (unit) network

	denoise image using deep neural network
	get image denoising network
	get denoising convolutional neural network layers

preprocess data with deterministic operations such as normalization or color space conversion, or augment training data with randomized operations such as random cropping or color jitter.
(deep learning toolbox)
learn how to use datastores in deep learning applications.
(deep learning toolbox)
此示例说明如何准备数据存储，以便使用 imagedatastore 的 transform 和 combine 函数来训练图像到图像的回归网络。
this example shows how you can perform common kinds of randomized image augmentation such as geometric transformations, cropping, and adding noise.

use a pretrained neural network to remove gaussian noise from a grayscale image, or train your own network using predefined layers.
you can create and customize deep learning networks that follow a modular pattern with repeating groups of layers, such as u-net and cyclegan.
get started with gans for image-to-image translation
transfer styles and characteristics from one set of images to the scene content of other images by using generative adversarial networks (gans).
预训练的深度神经网络 (deep learning toolbox)
了解如何下载和使用预训练的卷积神经网络进行分类、迁移学习和特征提取。
(deep learning toolbox)
探索 matlab^® 中的所有深度学习层。

在 matlab 中进行深度学习 (deep learning toolbox)
通过使用卷积神经网络进行分类和回归来探索 matlab 的深度学习能力，包括预训练网络和迁移学习，以及在 gpu、cpu、集群和云上进行训练。
semantic segmentation using deep learning (computer vision toolbox)
this example shows how to segment an image using a semantic segmentation network.