INCEPTION - 翻译成英语

• inception

在 中文 中使用 Inception 的示例及其翻译为 英语

换装：该用户认为倪家骏(NathanAdrian)是该《盗梦空间》(Inception)演员的“运动版”.
Changing it up: This user reckons that Nathan is an'athletic version' of the Inception actor.

比如在ImageNet上进行128×128分辨率的训练后，它的InceptionScore(IS)得分为166.3，是之前最佳得分52.52分的3倍。
For example, after performing 128×128 resolution training on ImageNet, its Inception Score(IS) score is 166.3, which is the best score of 52.52 points and 3 times.

但更重要的是，Inception展现了经过良好设计的「网中有网」架构的能力，让神经网络的表征能力又更上了一层楼。
Most importantly, however, Inception demonstrated the power of well-designed“network-in-network” architectures, adding yet another step to the representational power of neural networks.

他们陆续推出了以下几个模型，每一个都比上一个有所改进，且每一次都取得了新的领先成果：QuocNet、AlexNet、Inception(GoogLeNet)、BN-Inception-v2。
Successive models continue to show improvements, each time achieving a new state-of-the-art result: QuocNet, AlexNet, Inception(GoogLeNet), BN-Inception-v2.

修改代码以构建不同的图像数据集，并从公共模型集合（例如，Inception、VGG、ResNet、AlexNet和MobileNet）中进行选择。
Modify the code to build different image data sets and select from a collection of public models, such as Inception, VGG, ResNet, AlexNet, and MobileNet.

例如，**瓶颈(bottleneck)结构及1×1卷积**这种设计理念已经被广泛用于Inception和ResNet系列网络设计中。
The bottleneck structure or 1x1 convolution: This kind of design concept has already got widely applied in the Inception and ResNet series of network designs.

在这项研究中，我们尝试了各种神经网络，用于最近基于深度学习的模型，如PNASNet-5-Large，InceptionResNetV2，SENet154，InceptionV4。
In this study, we experimented with various neural networks which employ recent deep learning based models like PNASNet-5-Large, InceptionResNetV2, SENet154, InceptionV4.

Inception是本好电影。
Inception is a good movie.

最喜欢的电影：Inception.
My favorite movies: Inception.

最喜欢的电影：Inception.
MY favorite movie is"Inception".

看的电影是《Inception》。
We saw the movie,"Inception.".

在ImageNet上训练的InceptionV3.
Inception V3 trained on Imagenet.

对，这个电影大家都看过：Inception。?
And you know that film everyone loved: Inception?

首先，要下载inceptionresnetv2网络并加载权重。
First, we download the Inception ResNet v2 neural network and load the weights.

这个盒子被称为Inception模型。
This box is called an Inception module.

Inceptionv3和MobileNets已经在ImageNet数据集上训练。
Inception v3 and MobileNets have been trained on the ImageNet dataset.

这些比例在各个Inception块中都略有不同。
These ratios are slightly different in different Inception blocks.

在Inception中，我们开始将两者稍微分开。
In Inception, we began separating the two slightly.

最终架构包括堆叠在一起的多个inception模块。
The final architecture contains multiple of these inception modules stacked one over the other.

首先，我们下载InceptionResNetv2神经网络，加载权重。
First, we download the Inception ResNet v2 neural network and load the weights.