Conv1D的输入输出:
import tensorflow as tf
from tensorflow.keras import layers
con1 = layers.Conv1D(1, kernel_size=1, padding='same', activation=tf.nn.relu, input_shape=(2, 2))
model = tf.keras.Sequential()
model.add(con1)
print(model.input_shape)
print(model.output_shape)
'''
(None, 2, 2)
(None, 2, 1)
'''