“邓维宁”版本间的差异
来自iCenter Wiki
第30行: | 第30行: | ||
model.fit(x_train, y_train, epochs=5) | model.fit(x_train, y_train, epochs=5) | ||
model.evaluate(x_test, y_test) | model.evaluate(x_test, y_test) | ||
+ | |||
+ | |||
+ | === 10.27操作 === | ||
+ | |||
+ | [https://playground.tensorflow.org/ 神经网络拟合游戏] | ||
+ | <br /><br /> | ||
+ | |||
+ | |||
+ | [https://piano-scribe.glitch.me/ 音乐序列拟合]<br /> | ||
+ | <br /> | ||
+ | |||
+ | [https://github.com/tflearn/tflearn/blob/master/examples/basics/multiple_regression.py multiple_regression.py]<br /> | ||
+ | <br /> |
2018年10月27日 (六) 12:32的最后版本
基本信息
邓维宁,重庆人,社科74班,心理学专业
兴趣特长
吃火锅,运动,如乒乓球、羽毛球、网球。
爱好睡觉,阅读,C++。
10.20 操作
C:\Users\dell>pip install jupyter notebook
import tensorflow as tf mnist = tf.keras.datasets.mnist
(x_train, y_train),(x_test, y_test) = mnist.load_data() x_train, x_test = x_train / 255.0, x_test / 255.0
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(), tf.keras.layers.Dense(512, activation=tf.nn.relu), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10, activation=tf.nn.softmax)
]) model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5) model.evaluate(x_test, y_test)