python - tensorflow 损失始终为 0.0

Question

我已经完成了 senddex 的教程。但是当我执行程序时，损失始终为0.0。

Epoch 0 completed out of 10 loss: 0.0
Epoch 1 completed out of 10 loss: 0.0
Epoch 2 completed out of 10 loss: 0.0
Epoch 3 completed out of 10 loss: 0.0
Epoch 4 completed out of 10 loss: 0.0
Epoch 5 completed out of 10 loss: 0.0
Epoch 6 completed out of 10 loss: 0.0
Epoch 7 completed out of 10 loss: 0.0
Epoch 8 completed out of 10 loss: 0.0
Epoch 9 completed out of 10 loss: 0.0
Accuracy: 0.0

我找不到任何解决方案。

import numpy as np

import tensorflow as tf

old_v = tf.logging.get_verbosity()
tf.logging.set_verbosity(tf.logging.ERROR)

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500

n_classes = 10
batch_size = 100

x = tf.placeholder('float', [None, 784])
y = tf.placeholder('float')


def neural_network_model(data):
    hidden_1_layer = {'weights': tf.Variable(tf.random_normal([784, n_nodes_hl1])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl1]))}

    hidden_2_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl2]))}

    hidden_3_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl3]))}

    output_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
                    'biases': tf.Variable(tf.random_normal([n_classes])), }

    l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
    l1 = tf.nn.relu(l1)

    l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']), hidden_2_layer['biases'])
    l2 = tf.nn.relu(l2)

    l3 = tf.add(tf.matmul(l2, hidden_3_layer['weights']), hidden_3_layer['biases'])
    l3 = tf.nn.relu(l3)

    output = tf.matmul(l3, output_layer['weights']) + output_layer['biases']

    return output


def train_neural_network(x):
    prediction = neural_network_model(x)
    # OLD VERSION:
    # cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
    # NEW:
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
    optimizer = tf.train.AdamOptimizer().minimize(cost)

    hm_epochs = 10
    with tf.Session() as sess:
        # OLD:
        # sess.run(tf.initialize_all_variables())
        # NEW:
        sess.run(tf.global_variables_initializer())

        for epoch in range(hm_epochs):
            epoch_loss = 0
            for _ in range(int(mnist.train.num_examples / batch_size)):
                epoch_x, epoch_y = mnist.train.next_batch(batch_size)
                _, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y: epoch_y})
                epoch_loss += c

            print('Epoch', epoch, 'completed out of', hm_epochs, 'loss:', epoch_loss)

        correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))

        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        print('Accuracy:', accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))


train_neural_network(x)

这是完整的代码。为了确保我写的一切正确，我从网站上复制了代码。

我没有收到任何错误，但损失值没有增加甚至没有变化。

你能帮我一下吗？

埃利亚斯

Answer 1

损失并非为零。即使在您粘贴的要附加的代码中(epoch_loss += c)，它也会为我打印累积损失。

您的代码的稍微修改版本是这样的。它绘制了损失

import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf

old_v = tf.logging.get_verbosity()
tf.logging.set_verbosity(tf.logging.ERROR)

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500

n_classes = 10
batch_size = 100

x = tf.placeholder('float', [None, 784])
y = tf.placeholder('float')


def neural_network_model(data):
    hidden_1_layer = {'weights': tf.Variable(tf.random_normal([784, n_nodes_hl1])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl1]))}

    hidden_2_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl2]))}

    hidden_3_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl3]))}

    output_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
                    'biases': tf.Variable(tf.random_normal([n_classes])), }

    l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
    l1 = tf.nn.relu(l1)

    l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']), hidden_2_layer['biases'])
    l2 = tf.nn.relu(l2)

    l3 = tf.add(tf.matmul(l2, hidden_3_layer['weights']), hidden_3_layer['biases'])
    l3 = tf.nn.relu(l3)

    output = tf.matmul(l3, output_layer['weights']) + output_layer['biases']

    return output


def train_neural_network(x):
    prediction = neural_network_model(x)
    # OLD VERSION:
    # cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
    # NEW:
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)

    hm_epochs = 10
    with tf.Session() as sess:
        # OLD:
        # sess.run(tf.initialize_all_variables())
        # NEW:
        sess.run(tf.global_variables_initializer())

        epoch_loss = []
        for epoch in range(hm_epochs):
            for _ in range(int(mnist.train.num_examples / batch_size)):
                epoch_x, epoch_y = mnist.train.next_batch(batch_size)
                _, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y: epoch_y})
                epoch_loss.append(c)
                print('Epoch', epoch, 'completed out of', hm_epochs, 'loss:', c)

        correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))

        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        print('Accuracy:', accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

        plt.subplot(1, 2, 1)
        plt.plot(epoch_loss)
        plt.title('Epoch Loss')
        plt.show()

train_neural_network(x)