conv卷积基础

小yuning

已于 2023-02-06 15:04:35 修改

阅读量543

点赞数 1

分类专栏：算法基础文章标签： cnn

于 2022-01-11 10:57:47 首次发布

本文链接：https://blog.csdn.net/weixin_38502514/article/details/122368860

版权

cnn基础

一维卷积 Conv1d

tf.keras.layers.Conv1D(
    filters, kernel_size, strides=1, padding='valid',
    data_format='channels_last', dilation_rate=1, groups=1,
    activation=None, use_bias=True, kernel_initializer='glorot_uniform',
    bias_initializer='zeros', kernel_regularizer=None,
    bias_regularizer=None, activity_regularizer=None, kernel_constraint=None,
    bias_constraint=None, **kwargs
)

示例1：

# The inputs are 128-length vectors with 10 timesteps, and the batch size is 4.
input_shape = (4, 10, 128)
x = tf.random.normal(input_shape)
y = tf.keras.layers.Conv1D(
32, 3, activation='relu',input_shape=input_shape[1:])(x)