网络总是在不同的测试样本上预测相同的类别

Question

我正在尝试从训练后保存的训练模型中预测单个MNIST图像。 但是，每当我尝试打印预测（末尾的分类变量）时，输入的每个不同图像都会得到“ 0”。 我在网上看了一下，但只能找到模型的评估，而不能找到如何预测单个事物的评估。 如果可能的话，请向我显示文档或这样做的方法。

import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
batch_size = 128
test_size = 256

def init_weights(shape):
    return tf.Variable(tf.random_normal(shape, stddev=0.01))

def model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden):
    l1a = tf.nn.relu(tf.nn.conv2d(X, w,                       # l1a shape=(?, 28, 28, 32)
                        strides=[1, 1, 1, 1], padding='SAME'))
    l1 = tf.nn.max_pool(l1a, ksize=[1, 2, 2, 1],              # l1 shape=(?, 14, 14, 32)
                        strides=[1, 2, 2, 1], padding='SAME')
    l1 = tf.nn.dropout(l1, p_keep_conv)

    l2a = tf.nn.relu(tf.nn.conv2d(l1, w2,                     # l2a shape=(?, 14, 14, 64)
                        strides=[1, 1, 1, 1], padding='SAME'))
    l2 = tf.nn.max_pool(l2a, ksize=[1, 2, 2, 1],              # l2 shape=(?, 7, 7, 64)
                        strides=[1, 2, 2, 1], padding='SAME')
    l2 = tf.nn.dropout(l2, p_keep_conv)

    l3a = tf.nn.relu(tf.nn.conv2d(l2, w3,                     # l3a shape=(?, 7, 7, 128)
                        strides=[1, 1, 1, 1], padding='SAME'))
    l3 = tf.nn.max_pool(l3a, ksize=[1, 2, 2, 1],              # l3 shape=(?, 4, 4, 128)
                        strides=[1, 2, 2, 1], padding='SAME')
    l3 = tf.reshape(l3, [-1, w4.get_shape().as_list()[0]])    # reshape to (?, 2048)
    l3 = tf.nn.dropout(l3, p_keep_conv)

    l4 = tf.nn.relu(tf.matmul(l3, w4))
    l4 = tf.nn.dropout(l4, p_keep_hidden)

    pyx = tf.matmul(l4, w_o)
    return pyx

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
trX = trX.reshape(-1, 28, 28, 1)  # 28x28x1 input img
teX = teX.reshape(-1, 28, 28, 1)  # 28x28x1 input img

X = tf.placeholder("float", [None, 28, 28, 1])
Y = tf.placeholder("float", [None, 10])

w = init_weights([3, 3, 1, 32])       # 3x3x1 conv, 32 outputs
w2 = init_weights([3, 3, 32, 64])     # 3x3x32 conv, 64 outputs
w3 = init_weights([3, 3, 64, 128])    # 3x3x32 conv, 128 outputs
w4 = init_weights([128 * 4 * 4, 625]) # FC 128 * 4 * 4 inputs, 625 outputs
w_o = init_weights([625, 10])         # FC 625 inputs, 10 outputs (labels)

p_keep_conv = tf.placeholder("float")
p_keep_hidden = tf.placeholder("float")
py_x = model(X, w, w2, w3, w4, w_o, p_keep_conv, p_keep_hidden)

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y))
train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost)
predict_op = tf.argmax(py_x, 1)
saver = tf.train.Saver()

with tf.Session() as sess:
    # you need to initialize all variables
    tf.global_variables_initializer().run()

    for i in range(100):
        training_batch = zip(range(0, len(trX), batch_size),
                             range(batch_size, len(trX)+1, batch_size))
        for start, end in training_batch:
            sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end],
                                          p_keep_conv: 0.8, p_keep_hidden: 0.5})

        test_indices = np.arange(len(teX)) # Get A Test Batch
        np.random.shuffle(test_indices)
        test_indices = test_indices[0:test_size]

        print(i, np.mean(np.argmax(teY[test_indices], axis=1) ==
                         sess.run(predict_op, feed_dict={X: teX[test_indices],
                                                         Y: teY[test_indices],
                                                         p_keep_conv: 1.0,
                                                         p_keep_hidden: 1.0})))
    save_path = saver.save(sess, "tmp/model.ckpt")
    print("Model saved in file: %s" % save_path)

这是我为了能够预测单个图像而编写的代码，但是“分类”返回“ 0”。 它不应该返回热编码的索引吗？

with tf.Session() as sess:
    # Restore variables from disk.
    saver.restore(sess, "tmp/model.ckpt")
    print "...Model Loaded..."
    tf.global_variables_initializer().run()
    classification = sess.run(tf.argmax(predict_op, -1), feed_dict={X: trX[26].reshape(1,28,28,1),p_keep_conv: 1.0,p_keep_hidden: 1.0})
    print classification

Answer 1

加载/还原后不要初始化变量（ tf.global_variables_initializer().run() ）。 否则，您的训练变量将被覆盖。

编辑 ：

另外， sess.run(tf.argmax(predict_op, -1), ...正在使用predict_op = tf.argmax(py_x, 1)应将其更改为仅一个argmax操作：

with tf.Session() as sess:
    # Restore variables from disk.
    saver.restore(sess, "tmp/model.ckpt")
    print("...Model Loaded...")
    # tf.global_variables_initializer().run()  # <-- do not run this
    classification = sess.run(predict_op,  # <-- no second argmax
                              feed_dict={X: teX[26].reshape(1,28,28,1),  # <-- use test set
                                         p_keep_conv: 1.0,
                                         p_keep_hidden: 1.0}
                              )
    print(classification)

另外，您可能要在测试集（teX，teY）上进行测试，而不是训练集（trX，trY）进行测试。

Answer 2

我发现错误是：

classification = sess.run(tf.argmax(predict_op, -1),
                          feed_dict={X: teX[2].reshape(1,28,28,1),
                                     p_keep_conv: 1.0,
                                     p_keep_hidden: 1.0})

应该：

classification = sess.run(predict_op,
                          feed_dict={X: teX[2].reshape(1,28,28,1),
                                     p_keep_conv: 1.0,
                                     p_keep_hidden: 1.0})