汉译英：UNets在图像分析方面具有强大的能力可以精确地描述图像。在图像分割中训练了几个致力于图像分割的最先进的深度学习UNet神经网络模型。评估的UNet架构为FCN8、UNet、Attention UNet、Channel UNet、ResNet34 UNet、UNet++。下文简要介绍了每种模型的主要特征。

UNets have powerful capabilities in image analysis and can accurately describe images. Several state-of-the-art deep learning UNet neural network models dedicated to image segmentation have been trained in image segmentation. The evaluated UNet architectures include FCN8, UNet, Attention UNet, Channel UNet, ResNet34 UNet, and UNet++. The main features of each model are briefly introduced in the following text.