在給定的4D input與filter下計算2D卷積輸入shape為[batch, height, width, in_channels]

TensorFlow的CNN代碼中有

tf.nn.conv2d(X,?W1,?strides=[1,?1,?1,?1],?padding='SAME')??

這樣一句，本文介紹tf.nn.conv2d的用法：
tf.nn.conv2d tf.nn.conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None, data_format=None, name=None)
Computes a 2-D convolution given 4-D input and filter tensors.
Given an input tensor of shape [batch, in_height, in_width, in_channels] and a filter / kernel tensor of shape [filter_height, filter_width, in_channels, out_channels], this op performs the following:
Flattens the filter to a 2-D matrix with shape [filter_height * filter_width * in_channels, output_channels]. Extracts image patches from the input tensor to form a virtual tensor of shape [batch, out_height, out_width, filter_height * filter_width * in_channels]. For each patch, right-multiplies the filter matrix and the image patch vector. In detail, with the default NHWC format,
output[b, i, j, k] = sum_{di, dj, q} input[b, strides[1] * i + di, strides[2] * j + dj, q] * filter[di, dj, q, k] Must have strides[0] = strides[3] = 1. For the most common case of the same horizontal and vertices strides, strides = [1, stride, stride, 1].
Args:
input: A Tensor. Must be one of the following types: half, float32, float64. 輸入一個4維數(shù)據(jù)[batch, in_height, in_width, in_channels] ； filter: A Tensor. Must have the same type as input. 過濾器，也是一個4維的Tensor[filter_height, filter_width, in_channels, out_channels] strides: A list of ints. 1-D of length 4. The stride of the sliding window for each dimension of input. Must be in the same order as the dimension specified with format.卷積滑動步長 padding: A string from: "SAME", "VALID". The type of padding algorithm to use.邊緣填充.簡單理解SAME是邊緣填0，左邊（上邊）補0的個數(shù)和右邊（上邊）補0的個數(shù)一樣或少一個；VALID不補，多余的還丟棄。 參考1：https://www.tensorflow.org/api_docs/python/nn/convolution#convolution 參考2： use_cudnn_on_gpu: An optional bool. Defaults to True. data_format: An optional string from: "NHWC", "NCHW". Defaults to "NHWC". Specify the data format of the input and output data. With the defaultformat"NHWC", the data is stored in the order of: [batch, in_height, in_width, in_channels]. Alternatively, the format could be "NCHW", the data storage order of: [batch, in_channels, in_height, in_width]. name: A name for the operation (optional). Returns:
A Tensor. Has the same type as input.

總結

以上是生活随笔為你收集整理的TensorFlow学习笔记（十七）tf.nn.conv2d的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內容還不錯，歡迎將生活随笔推薦給好友。