What is the translation of " THE CONVOLUTION " in Chinese?

• 卷积
• 的卷积

Examples of using The convolution in English and their translations into Chinese

Out_channels(int)- Number of channels produced by the convolution.
Out_channels(int)-卷积产生的通道.

The convolution happens only in the time dimension, not in the frequency dimension.
卷积仅仅在时间维度出现，而不在频率维度。

Out_channels(int)- Number of channels produced by the convolution.
Out_channels(int)-卷积产生的通道数.

To differentiate it from the convolution step, we call it a“fully connected” network.
为了区分它和卷积的不同，我们把它称作“全连接”网络（“FullyConnected”Network）。

Out_channels(python: int)- Number of channels produced by the convolution.
Out_channels(int)-卷积产生的通道数.

After the convolution(matrix multiplication), we down-sample the large image into a small output image.
经过卷积（矩阵乘法）后，我们将大图像下采样为小图像。

When we stride a filter, we skip over parts of the input between applications of the convolution.
当我们跨越过滤器时，我们跳过卷积应用之间的部分输入。

Since the convolutions are divided into several paths, each path can be handled separately by different GPUs.
因为卷积被拆分到几条道路中，每条道路都由不同的GPU别离进行处理。

The spectrum of the sampled signal Y(f) it turns out will actually be the convolution of X(f) with W(f).
它结果的采样信号Y（f）的频谱实际上是X（f）与W（f）的卷积。

Note: The convolution layers in YOLO don't actually use bias, so b is zero in the above equation.
注意：事实上，YOLO中的卷积层没有使用偏差项，因此上述公式中b为0。

To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation.
为了训练的更快，我们使用了非饱和神经元并对卷积操作进行了非常有效的GPU实现。

The figure below shows the convolution of two square pulses(blue and red) and the results.
下面的图片显示了两个矩形脉冲（蓝色和红色）的卷积运算及其结果。

We can see that when the second element of the first column is output, the convolution window slides down three rows.
可以看到，输出第一列第二个元素时，卷积窗口向下滑动了三行。

Note: The convolution layers in YOLO don't actually use bias, so b is zero in the above equation.
注意：实际上在YOLO中，卷积层并没有使用偏置量，所以b在上面的等式中始终是0。

In the image, the 3 x 3 red dots indicate that after the convolution, the output image is with 3 x 3 pixels.
在图中，3x3的红点表明，卷积后，输出图像是3x3像素。

The name“convolutional neural networks” indicates that the network employs a mathematical operation called the convolution.
名称“卷积神经网络”表示网络采用称为卷积的数学运算。

In the image, the 3 x 3 red dots indicate that after the convolution, the output image is with 3 x 3 pixels.
在图像中，3×3个红点表示在卷积之后，输出图像具有3×3像素。

The name“convolutional neural networks” indicates that the network employs a mathematical operation called the convolution.
卷积神经网络”一词表明该网络使用了卷积(convolution)这种数学运算。

In the image, the 3 x 3 red dots indicate that after the convolution, the output image is with 3 x 3 pixels.
在这张图像中，3×3的红点表示经过卷积后，输出图像是3×3像素。

Then, the Convolution of the 5 x 5 image and the 3 x 3 matrix can be computed as shown in the animation in Figure 5 below:.
接下来，5x5的图像和3x3的矩阵的卷积可以按下图所示的动画一样计算：.

This level includes the fully connected neural network(FCN) and the convolution network(CNN) and various combinations of them.
涉及到的系统包含全链接神经网络（FCN）、卷积网络（CNN）以及它们的各种组合。

And you remember during the convolution operation, you were taking these 27 numbers, or really well, 27 times 2, because you have two filters.
在卷积过程中，我们对这27个数进行操作，其实是27×2，因为我们用了两个过滤器，我们取这些数做乘法。

This level includes the fully connected neural network(FCN) and the convolution network(CNN) and various combinations of them.
这个级别包括完全连接神经网络（FCN）和卷积神经网络（CNN）以及它们的各种组合。

The convolution layer tries to analyze each small patch of the neural network in depth, resulting in a higher abstraction feature representation.
卷积层试图将神经网络中的每一小块进行更加深入地分析从而得到抽象程度更高的特征。

The size of the Feature Map(Convolved Feature) is controlled by three parameters[4] that we need to decide before the convolution step is performed:.
特征映射（卷积特征）的大小由我们在执行卷积步骤之前需要决定的三个参数[4]控制：.

This is precisely the convolution of u with the tempered distribution pp. v. 1/πt(due to Schwartz(1950); see Pandey(1996, Chapter 3)).
这就是u与缓增分布pp.v.1/πt的卷积（由于Schwartz(1950)；参见Pandey(1996，Chapter3)）。

In SAGAN, the self-attention module works in conjunction with the convolution network and uses the key-value-query model(Vaswani, et al., 2017).
在SAGAN中，注意力模块与卷积神经网络协同工作，并且使用了key-value-query模型（Vaswani等，2017）。

The convolution layer, for example, adds a dimension and changes the value of length and width according to the characteristics of the convolution kernel(filter).
例如卷积层，会增加一个维度，并且根据卷积核（过滤器）的特征改变长宽的值。

Let's move on to talk about how to handle the convolution in the other two directions(height& width), as well as important convolution arithmetic.
接下来评论一下怎样处理在其他两个方向（高&宽）中的卷积，以及重要的卷积算法（convolutionarithmetic）。