iT邦幫忙

1

Day25 參加職訓(機器學習與資料分析工程師培訓班),Python程式設計

  • 分享至 

  • xImage
  •  

建立網路的其他寫法

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

Model01 = Sequential([Dense(512, activation='relu', input_dim=3),
                      Dense(1, activation='sigmoid')])
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Activation

Model02 = Sequential([Dense(512, input_dim=3), Activation('relu'),
                     Dense(1), Activation('sigmoid')])
Model02.summary()

https://ithelp.ithome.com.tw/upload/images/20210803/20139039AvlqgonSvt.png

# 儲存網路配置 config
Config_Model02 = Model02.get_config()
from tensorflow.keras.models import Sequential
Model03 = Sequential.from_config(Config_Model02)
Model03.summary()  #會發現與Model02的網路一樣

# 儲存網路配置 json
Config_json_Model03 = Model03.to_json()

from tensorflow.keras.models import model_from_json

Model04 = model_from_json(Config_json_Model03)
# 取得權重
model_weights = model.get_weights()
# 儲存權重
MNIST_Model.save_weights('MNIST.Weights')
# 回復權重
model06.load_weights('MNIST.Weights')
from tensorflow.keras.optimizers import RMSprop
# 修改優化器的預設值
My_RMSprop = RMSprop(learning_rate=0.01)
MNIST_Model.compile(optimizer=My_RMSprop, loss = 'categorical_crossentropy', metrics=['accuracy'])
MNIST_Model.fit(X_train, y_train, epochs=5, batch_size=128, verbose=1)

圖片
  直播研討會
圖片
{{ item.channelVendor }} {{ item.webinarstarted }} |
{{ formatDate(item.duration) }}
直播中

尚未有邦友留言

立即登入留言