Question

我正在使用32g ram的2018 MBP在jupyter中运行tensorflow代码。该代码来自Geron的“使用Scikit-Learn和TensorFlow进行动手式机器学习”的第9章。代码成功运行直到代码调用.eval或.run的某一时刻内核死亡。

https://github.com/ageron/handson-ml/blob/master/09_up_and_running_with_tensorflow.ipynb

代码包含在上面。

将上面链接的代码剪切并粘贴到我自己的Jupyter笔记本上，然后运行会导致单元格19中的内核死亡：

import numpy as np
from sklearn.datasets import fetch_california_housing

reset_graph()

housing = fetch_california_housing()
m, n = housing.data.shape
housing_data_plus_bias = np.c_[np.ones((m, 1)), housing.data]

X = tf.constant(housing_data_plus_bias, dtype=tf.float32, name="X")
y = tf.constant(housing.target.reshape(-1, 1), dtype=tf.float32, name="y")
XT = tf.transpose(X)
theta = tf.matmul(tf.matmul(tf.matrix_inverse(tf.matmul(XT, X)), XT), y)

with tf.Session() as sess:
    theta_value = theta.eval()

以及单元格25中：

reset_graph()

n_epochs = 1000
learning_rate = 0.01

X = tf.constant(scaled_housing_data_plus_bias, dtype=tf.float32, name="X")
y = tf.constant(housing.target.reshape(-1, 1), dtype=tf.float32, name="y")
theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name="theta")
y_pred = tf.matmul(X, theta, name="predictions")

error = y_pred - y
mse = tf.reduce_mean(tf.square(error), name="mse")

gradients = 2/m * tf.matmul(tf.transpose(X), error)

training_op = tf.assign(theta, theta - learning_rate * gradients)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        if epoch % 100 == 0:
            print("Epoch", epoch, "MSE =", mse.eval())
        sess.run(training_op)

    best_theta = theta.eval()

要找到问题，我尝试在最后一个单元中成功运行mse.eval（）和sess.run（training_op）。如果最后一节是

，那不会杀死内核

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        if epoch % 100 == 0:
            print("Epoch", epoch, "MSE =")

或者如果是：

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        print('hi')
    best_theta = theta.eval()

但它因以下两个原因而死亡：

（1）

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        if epoch % 100 == 0:
            print("Epoch", epoch, "MSE =", mse.eval())

（2）

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        sess.run(training_op)

我还在Spyder中尝试了此代码，然后重新安装了tensorflow。结果相同。 Geron的书第9章中的类似代码扼杀了我的内核，在我喜欢他的书的指导时，我想继续。

TensorFlow导致内核死于.eval或.run

0 个答案: