What is the translation of " FEATURE MAP " in Chinese?

• 特征映射
• 中的特征图连

Examples of using Feature map in English and their translations into Chinese

All units in a feature map share the same filter bank.
特征映射中的所有单元共享相同的滤波器组.。

Now, the first thing to notice is our output is a feature map.
现在，首先要注意的是我们的输出是一个特征图。

This is because any single feature map only uses inputs from the same GPU.
这是因为任何单一的特征映射仅仅使用来自同一个GPU的输入。

To perform image recognition, we need more than one feature map.
为了完成图像识别我们需要超过一个的特征映射。

Why not connect every S2 feature map to every C3 feature map?
为什么不把S2中的每个特征图连接到每个C3的特征图呢？原因有2点。?

This gives us the first element in the top-left corner of the feature map.
这给了我们特征映射左上角的第一个元素。

Note that the feature map has six elements, whereas our input has eight elements.
请注意，特征映射有六个元素，而我们的输入有八个元素。

As pointed earlier, the dimensions of the feature map will be 13 x 13.
如之前所述，特征图的维度会是13×13。

The output feature map here is also referred to as the‘Rectified' feature map.
这里的输出特征图也可以看作是“修正”过的特征图。

This gives the last element in the first full row of the feature map.
这给出了特征映射的第一个完整行中的最后一个元素。

Why not connect every S2 feature map to every C3 feature map?.
为什么不把S2中的每个特征图连接到每个C3的特征图呢？?

We already know that the transposed convolution layer can magnify a feature map.
我们已经知道，转置卷积层可以放大特征图。

Both nodes have to vote on every single feature map, regardless of what it contains.
两个节点都必须对每个特征图进行投票，无论它包含什么。

A filter(with red outline) slides over the input image(convolution operation) to produce a feature map.
一个过滤器（红色边框）在输入图像上移动（卷积操作）以生成特征映射。

Next, the filter is applied to the input pattern and the feature map is calculated and displayed.
接下来，滤波器应用到输入模式，计算并显示出特征映射。

The shape of the feature map output will be four-dimensional with the shape[batch, rows, columns, filters].
特征映射的输出shape将是四维的，[批，行，列，滤波器]。

As seen, using six different filters produces a feature map of depth six.
如图所示，使用六个不同的过滤器得到深度为六的特征映射。

In the image below, we get the feature map after applying the first grouped convolution GConv1 with 3 filter groups.
下图中，显示了应用有3个过滤器组的第一个分组卷积GConv1后所得到的特征映射。

As seen, using six different filters produces a feature map of depth six.
如图可见，使用六个不同的滤波器得到一个深度为六的特征图。

This will return the feature map directly: that is the output of applying the filter systematically across the input sequence.
这将直接返回特征映射：这是在输入序列中系统地应用滤波器的输出。

This network is able to just look at the last convolutional feature map and produce region proposals from that.
这个网络能够查看最后的卷积特征映射，并从中产生区域提议。

This module takes the feature map, created by the convolutional neural network, and transforms it into three feature spaces.
这个模块以卷积神经网络创建的特征图为输入，并且将它们转换成了三个特征空间。

Consecutive frames are used as time steps in our sequence, and a feature map is extracted for each frame using the CNN model.
连续的图像帧在序列中作为时间步，每个帧使用CNN模型来提取特征图。

The second layer gets as input 20 dimensional vectors(10 from the input and 10 from the previous layer) and calculates another 10 feature maps.
第二层作为输入20维向量（来自输入的10个，前一层的10个），并计算另外10个特征图。

You can think of these three feature maps as stacked 2d matrices, so, the‘depth' of the feature map would be three.
你可以把这三个特征图看作是堆叠的2d矩阵，那么，特征图的“深度”就是三。

Here, an 11 x 11 weight matrix is convolved in parallel with an 11 x 11 input feature map to create one output value.
在这里，将11x11的权值矩阵与一个11x11的输入特征图并行求卷积，以产生一个输出值。

Essentially, these score maps are convolutional feature maps that have been trained to recognize certain parts of each object.
本质上来讲，这些分数图都是卷积特征图，它们被训练来识别每个目标的特定部位。

Combining the results from both filters, e.g. combining both feature maps, will result in all of the lines in an image being highlighted.
综合两个滤波器的结果，比如综合两个特征映射，将会突出显示图像中的所有的线。

Figures 8 and 9 show the activations of the first two feature map layers for two different example inputs, an unpaved road and a forest.
图8和图9展示了两个不同示例输入的头两层特征映射的激活，一条尚未铺砌的路和一片森林。

So, the more the“apple” node thinks a particular feature map contains“apple” features, the more votes it sends to that feature map.
因此，“苹果”节点认为某图包含“苹果”特征越多，它给该特征图的投票就越多。