convolution in tensorflow (tf.nn.conv)_convolution算子 tensorflow-优快云博客

本文详细解析了TensorFlow中卷积操作的概念及其应用。主要包括conv2d、depthwise_conv2d和separable_conv2d等不同类型的卷积运算，并讨论了它们之间的区别。此外，还介绍了tf.nn.conv系列函数在不同维度数据上的使用场景。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Understanding convolution in tensorflow

Points should be noticed

The convolution ops sweep a 2-D filter over a batch of images, applying the filter to each window of each image of the appropriate size. The different ops trade off between generic vs. specific filters:
conv2d: Arbitrary filters that can mix channels together.
depthwise_conv2d: Filters that operate on each channel independently.
separable_conv2d: A depthwise spatial filter followed by a pointwise
filter.

from:
Neural Network | TensorFlow
https://www.tensorflow.org/api_guides/python/nn#Convolution

Explanation of the equation in API of `tf.nn.conv2d`

这里写图片描述

b in yellow shadow is for travering through the batch with images.
the variables in green shadow is for locating a patch.
In the equation, di and dj loop variable to traverse through the height and width of the patch in one image.
~~I’m not very sure about this.
q is for traversing through the channels of the image, with the step of strike[3]. ~~

ref:
tf.nn.conv2d | TensorFlow
https://www.tensorflow.org/api_docs/python/tf/nn/conv2d

tf.nn.conv[1d, 2d, 3d]

There are tf.nn.conv1d, tf.nn.conv2d and tf.nn.conv3d. Problems are there, which to be choosed and what’s the difference.
I have not studied this deep. For I am using tensorflow to processing images, it seems tf.nn.conv2d is for me. From my perspective, the difference of them are as following.

tf.nn.conv1d is for some linear structure, text, sound or some others.
tf.nn.conv2d is for structure appeared to be 2-D, such as image.
tf.nn.conv3d is for something not familiar to me. It seems to be applied in signal processing.