问题描述
我正在用Tensorflow学习卷积神经网络.
I am learning convolutional neural network with Tensorflow.
对于 tf.nn.conv2d ，我有些疑问.它的参数之一是filter:
我不明白out_channels是什么意思.
假设输入图像是[1, 3, 3, 1].因此，大小为3xx，通道为1.
然后，我们有了一个过滤器[2, 2, 1, 5]，这意味着在过滤之后，我们将得到一个具有5个通道的大小为2x2(有效"填充)的图像.
Suppose input image is [1, 3, 3, 1]. So the size is 3xx and the channel is 1.
Then we have a filter [2, 2, 1, 5], which means after the filtering, we will have an image of size 2x2 ("valid" padding) with 5 channels.
5个渠道来自哪里?据我了解，过滤只能生成1个通道. Tensorflow在这里使用5种不同的过滤器功能吗?
Where are the 5 channels from? From my understanding, the filtering can only have 1 channel generated. Is Tensorflow using 5 different filter functions here?
推荐答案
filter参数如您所引用，="nofollow noreferrer"> tf.nn.conv2d 函数是尺寸为[filter_height, filter_width, in_channels, out_channels]的4D张量.此张量表示尺寸为filter_height x filter_width的out_channels滤镜的堆栈，将应用于具有in_channels通道的图像.
The filter argument to the tf.nn.conv2d function, as you quoted, is a 4D tensor of dimensions [filter_height, filter_width, in_channels, out_channels]. This tensor represents a stack of out_channels filters of dimension filter_height x filter_width, to be applied over an image with in_channels channels.
参数filter_height，filter_width和out_channels由您定义，而input_channels取决于您对tf.nn.conv2d的输入.
The parameters, filter_height, filter_width and out_channels are defined by you, whereas input_channels is dependent on your input to tf.nn.conv2d.
换句话说，尺寸为[2, 2, 1, 5]的滤波器张量表示要在1通道输入上应用的5不同的2 x 2滤波器，但是您可以将其完美地更改为[2, 2, 1, 7]或其他任何值否则会给您带来更好的结果.
In other words, a filter tensor with dimensions [2, 2, 1, 5], represents 5 different 2 x 2 filters to be applied over a 1-channel input, but you could perfectly change it to [2, 2, 1, 7], or whatever else gives you better results.
为进一步说明，在下面的gif中，您有一个[3, 3, 1, 1]张量滤波器，卷积在[1, 5, 5, 1]图像上.这意味着您只将1过滤器卷积在图像上.
To further illustrate, in the following gif you have a [3, 3, 1, 1] tensor filter convolving over a [1, 5, 5, 1] image. This means you have only 1 filter being convolved over the image.
这篇关于卷积神经网络中的滤波器如何生成多个通道?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！