Conv1d

>>> 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)
>>> print(y.shape)
(4, 8, 32)

input 参数解释：

batch_size =4
length =10 (string 中 有多个 char)
channels = 128 （每个char 对应的onehot编码)

output

batch_size =4
length =8 经过了滑动窗口的特征提取
channels =filter 设置了多少特征

Conv1d

tf.keras.layers.Conv1D(
    filters,  # 输出多个通道
    kernel_size, # 滑动窗口大小
    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
)