头歌Tensorflow核心模块

最新推荐文章于 2024-11-04 18:51:42 发布

醉卧星河2.0

最新推荐文章于 2024-11-04 18:51:42 发布

阅读量306

点赞数 4

文章标签： tensorflow neo4j 人工智能

本文链接：https://blog.csdn.net/m0_62710340/article/details/139649130

版权

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv1D, MaxPool1D, LSTM, BatchNormalization, Dropout, Flatten, Reshape
model = Sequential()
######### Begin########
# 1nd block 通道数 64
model.add(Conv1D(64, 3, activation="relu",
                 input_shape=(1, 1), padding="same"))
model.add(Conv1D(64, 3, activation="relu", padding="same"))
model.add(BatchNormalization(trainable=True))
model.add(MaxPool1D(pool_size=2, strides=1, padding='same'))
# 2nd block 通道数 128
model.add(Conv1D(128, 3, activation="relu", padding="same"))
model.add(Conv1D(128, 3, activation="relu", padding="same"))
model.add(BatchNormalization(trainable=True))
model.add(MaxPool1D(pool_size=2, strides=1, padding='same'))
# 3nd block 通道数 256
model.add(Conv1D(256, 3, activation="relu", padding="same"))
model.add(Conv1D(256, 3, activation="relu", padding="same"))
model.add(Conv1D(256, 3, activation="relu", padding="same"))
model.add(BatchNormalization(trainable=True))
model.add(MaxPool1D(pool_size=2, strides=1, padding='same'))
# 4nd block 通道数 512
model.add(Conv1D(512, 3, activation="relu", padding="same"))
model.add(Conv1D(512, 3, activation="relu", padding="same"))
model.add(Conv1D(512, 3, activation="relu", padding="same"))
model.add(BatchNormalization(trainable=True))
model.add(MaxPool1D(pool_size=2, strides=1, padding='same'))
# 5nd block 通道数 512
model.add(Conv1D(512, 3, activation="relu", padding="same"))
model.add(Conv1D(512, 3, activation="relu", padding="same"))
model.add(Conv1D(512, 3, activation="relu", padding="same"))
model.add(BatchNormalization(trainable=True))
model.add(MaxPool1D(pool_size=2, strides=1, padding='same'))
# 6nd block LSTM层
model.add(LSTM(512))
model.add(BatchNormalization(trainable=True))
# 7nd block 全连接层
model.add(Dense(512, activation='relu'))
model.add(Dense(128, activation='tanh'))
model.add(Dense(1, activation='linear'))  
########End########
model.summary()