【问题标题】:unable to get the updated value of tensor in tensorflow无法在tensorflow中获取张量的更新值
【发布时间】:2017-08-14 12:22:08
【问题描述】:

我使用下面的代码进行简单的逻辑回归。我能够得到 b 的更新值:b.eval() 在训练之前/之后的值是不同的。但是,W.eval() 的值保持不变。我想知道我犯了什么错误?谢谢!

from __future__ import print_function

import tensorflow as tf

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

# Parameters
learning_rate = 0.01
training_epochs = 20
batch_size = 100
display_step = 1

# tf Graph Input
x = tf.placeholder(tf.float32, [None, 784]) # mnist data image of shape 28*28=784
y = tf.placeholder(tf.float32, [None, 10]) # 0-9 digits recognition => 10 classes

# Set model weights
W = tf.Variable(tf.random_normal([784, 10]))
b = tf.Variable(tf.zeros([10]))

# Construct model
pred = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax

# Minimize error using cross entropy
cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), reduction_indices=1))
# Gradient Descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Initializing the variables
init = tf.global_variables_initializer()

# Launch the graph
with tf.Session() as sess:
    sess.run(init)

    print('W is:')
    print(W.eval())
    print('b is:')
    print(b.eval())
    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_xs,
                                                 y: batch_ys})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))

    print("Optimization Finished!")

    print('W is:')
    print(W.eval())
    print('b is:')
    print(b.eval())
    # Test model
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    # Calculate accuracy
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print("Accuracy:", accuracy.eval({x: mnist.test.images, y:     mnist.test.labels}))

【问题讨论】:

  • this
  • 我没有初始化全零。我使用随机正常初始化。另外,该模型在训练后具有较高的预测性能,因此W不能是零矩阵。

标签: python tensorflow


【解决方案1】:

当我们打印一个 numpy 数组时,只会打印初始值和最后一个值,并且在 MNIST 的情况下,这些权重索引不会更新,因为图像中的相应像素保持不变,因为所有数字都写入数组的中心部分或图像不沿边界区域。 从一个输入样本到另一个输入样本变化的实际像素是中心像素,因此只有那些相应的权重元素会得到更新。 要比较训练前后的权重,您可以使用 numpy.array_equal(w1, w2) 或者,您可以通过执行以下操作打印整个 numpy 数组: 导入 numpy numpy.set_printoptions(threshold='nan') 或者,您可以逐个元素进行比较,并仅打印那些相差一定阈值的数组值

【讨论】:

    猜你喜欢
    • 1970-01-01
    • 2020-06-22
    • 1970-01-01
    • 1970-01-01
    • 1970-01-01
    • 2018-05-13
    • 2017-07-17
    • 2020-02-03
    • 1970-01-01
    相关资源
    最近更新 更多