尝试在 python 中使用 tensorflow 实现卷积神经网络程序时，我不断收到奇怪的“无效语法”错误

Question

我目前使用的是 Google Colab 内置的 python 的任何版本（我相信它是 3.7、3.8 或 3.9）。 我正在尝试执行一个 CNN 程序，该程序可用于在不使用 Keras 的情况下识别图像，但我不断收到一个奇怪的错误消息：

File "<ipython-input-12-6518b14c949f>", line 91
    optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)
            ^
SyntaxError: invalid syntax

这是我目前拥有的完整代码：

!pip install tensorflow_datasets
!pip install --upgrade tensorflow
!pip install tensorflow-datasets
!pip install mnist
#!pip install tensorflow.examples.tutorials.mnist

import argparse
print ('argparse version: ', argparse.__version__)
import mnist
print ('MNIST version: ', mnist.__version__)
import tensorflow_datasets
print ('tensorflow_datasets version: ', tensorflow_datasets.__version__)
import tensorflow.compat.v1 as tf
print ('tf version: ', tf.__version__)
tf.disable_v2_behavior()
#from tensorflow.examples.tutorials.mnist import input_data


#def build_arg_parser():
#    parser = argparse.ArgumentParser(description='Build a CNN classifier \
#            using MNIST data')
#    parser.add_argument('--input-dir', dest='input_dir', type=str,
#            default='./mnist_data', help='Directory for storing data')
#    return parser

def get_weights(shape):
    data = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(data)

def get_biases(shape):
    data = tf.constant(0.1, shape=shape)
    return tf.Variable(data)

def create_layer(shape):
    # Get the weights and biases
    W = get_weights(shape)
    b = get_biases([shape[-1]])

    return W, b

def convolution_2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1],
            padding='SAME')

def max_pooling(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
            strides=[1, 2, 2, 1], padding='SAME')

if __name__ == '__main__':
    #args = build_arg_parser().parse_args()

    # Get the MNIST data
    mnist = tensorflow_datasets.load('mnist')

    # The images are 28x28, so create the input layer
    # with 784 neurons (28x28=784)
    x = tf.placeholder(tf.float32, [None, 784])

    # Reshape 'x' into a 4D tensor
    x_image = tf.reshape(x, [-1, 28, 28, 1])

    # Define the first convolutional layer
    W_conv1, b_conv1 = create_layer([5, 5, 1, 32])

    # Convolve the image with weight tensor, add the
    # bias, and then apply the ReLU function
    h_conv1 = tf.nn.relu(convolution_2d(x_image, W_conv1) + b_conv1)

    # Apply the max pooling operator
    h_pool1 = max_pooling(h_conv1)

    # Define the second convolutional layer
    W_conv2, b_conv2 = create_layer([5, 5, 32, 64])

    # Convolve the output of previous layer with the
    # weight tensor, add the bias, and then apply
    # the ReLU function
    h_conv2 = tf.nn.relu(convolution_2d(h_pool1, W_conv2) + b_conv2)

    # Apply the max pooling operator
    h_pool2 = max_pooling(h_conv2)

    # Define the fully connected layer
    W_fc1, b_fc1 = create_layer([7 * 7 * 64, 1024])

    # Reshape the output of the previous layer
    h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])

    # Multiply the output of previous layer by the
    # weight tensor, add the bias, and then apply
    # the ReLU function
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

    # Define the dropout layer using a probability placeholder
    # for all the neurons
    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    # Define the readout layer (output layer)
    W_fc2, b_fc2 = create_layer([1024, 10])
    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

    # Define the entropy loss and the optimizer
    y_loss = tf.placeholder(tf.float32, [None, 10])
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_loss))
    optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)

    # Define the accuracy computation
    predicted = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_loss, 1))
    accuracy = tf.reduce_mean(tf.cast(predicted, tf.float32))

    # Create and run a session
    sess = tf.InteractiveSession()
    init = tf.initialize_all_variables()
    sess.run(init)

    # Start training
    num_iterations = 21000
    batch_size = 75
    print('\nTraining the model....')
    for i in range(num_iterations):
        # Get the next batch of images
        batch = mnist.train.next_batch(batch_size)

        # Print progress
        if i % 50 == 0:
            cur_accuracy = accuracy.eval(feed_dict = {
                    x: batch[0], y_loss: batch[1], keep_prob: 1.0})
            print('Iteration', i, ', Accuracy =', cur_accuracy)

        Train on the current batch
        optimizer.run(feed_dict = {x: batch[0], y_loss: batch[1], keep_prob: 0.5})

    # Compute accuracy using test data
    print('Test accuracy =', accuracy.eval(feed_dict = {
            x: mnist.test.images, y_loss: mnist.test.labels,
            keep_prob: 1.0}))

最初，我的行有错误

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_loss))

但是在我查找之后，我发现将其切换为

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_conv, logits=y_)

会修复那个错误，我相信它确实做到了。

我的下一个错误（也是我无法弄清楚的错误）出现在该行的正下方

optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)

这是出现无效语法错误的地方。 我尝试将其切换为使用不同类型的优化器，例如

optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)

但这似乎没有用。 我找到了一些使用完全相同代码的资源，但似乎以某种方式运行了它——我只是不知道如何运行。

我还注意到，无论我做什么，我也无法安装或使用tensorflow.examples.tutorials.mnist

有没有人对如何正确安装/使用 tensorflow.examples.tutorials.mnist 或如何修复 AdamOptimizer 行的错误有任何想法？ 到目前为止，我仍然无法找到任何显示解决这些问题的方法的方法，这些方法实际上对我有用。 谢谢！

更新：一些好人让我知道这实际上只是我括号的问题。 我添加了丢失的一个并修复了另一个错误 - 更新的部分现在是这样的：

# Define the entropy loss and the optimizer
y_loss = tf.placeholder(tf.float32, [None, 10])
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_conv, logits=y_loss))
optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)  

但是，现在我在与以前相同的优化器行中收到以下错误：

ValueError: No gradients provided for any variable, check your graph for ops that do not support gradients, between variables ["<tf.Variable 'Variable:0' shape=(5, 5, 1, 32) dtype=float32_ref>", "<tf.Variable 'Variable_1:0' shape=(32,) dtype=float32_ref>", "<tf.Variable 'Variable_2:0' shape=(5, 5, 32, 64) dtype=float32_ref>", "<tf.Variable 'Variable_3:0' shape=(64,) dtype=float32_ref>", "<tf.Variable 'Variable_4:0' shape=(3136, 1024) dtype=float32_ref>", "<tf.Variable 'Variable_5:0' shape=(1024,) dtype=float32_ref>", "<tf.Variable 'Variable_6:0' shape=(1024, 10) dtype=float32_ref>", "<tf.Variable 'Variable_7:0' shape=(10,) dtype=float32_ref>", "<tf.Variable 'Variable_8:0' shape=(5, 5, 1, 32) dtype=float32_ref>", "<tf.Variable 'Variable_9:0' shape=(32,) dtype=float32_ref>", "<tf.Variable 'Variable_10:0' shape=(5, 5, 32, 64) dtype=float32_ref>", "<tf.Variable 'Variable_11:0' shape=(64,) dtype=float32_ref>", "<tf.Variable 'Variable_12:0' shape=(3136, 1024) dtype=float32_ref>", "<tf.Variable 'Variable_13:0' shape=(1024,) dtype=float32_ref>", "<tf.Variable 'Variable_14:0' shape=(1024, 10) dtype=float32_ref>", "<tf.Variable 'Variable_15:0' shape=(10,) dtype=float32_ref>"] and loss Tensor("Mean:0", shape=(), dtype=float32).

关于如何解决这个新错误的任何想法？ 我对 tensorflow 和 CNN 很陌生，所以我不确定“没有为任何变量提供梯度”应该指向什么。

Answer 1

对于遇到任何类似问题的任何其他人，这就是我最终做的事情：

1. 我的第一个错误是忘记了括号，所以我补充说

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_conv, logits=y_loss))

2. 然后这变成了 args 错误 - 所以我不得不在括号中切换 arguments

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_loss, logits=y_conv))

现在它工作正常，整个部分现在看起来像这样：

    y_loss = tf.placeholder(tf.float32, [None, 10])
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_loss, logits=y_conv))
    optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)