如何结合密集层使用 TensorFlow Dataset API

Question

我正在为TensorFlow 文档中显示的输入管道试用 Dataset API，并使用几乎相同的代码：

tr_data = Dataset.from_tensor_slices((train_images, train_labels))
tr_data = tr_data.map(input_parser, NUM_CORES, output_buffer_size=2000)
tr_data = tr_data.batch(BATCH_SIZE)
tr_data = tr_data.repeat(EPOCHS)

iterator = dataset.make_one_shot_iterator()
next_example, next_label = iterator.get_next()

# Script throws error here
loss = model_function(next_example, next_label)

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

     while True:
        try:
            train_loss = sess.run(loss)
        except tf.errors.OutOfRangeError:
            print("End of training dataset.")
            break

这应该更快，因为它避免使用慢速 feed_dicts。但是我不能让它与我的模型一起工作，这是一个简化的 LeNet 架构。该问题是tf.layers.dense在我model_function()这期待一个已知输入形状（我猜是因为它必须知道权重的数目事先）。但是next_example，next_label只有通过在会话中运行它们才能获得它们的形状。在评估它们之前，它们的形状是不确定的?

声明model_function()抛出此错误：

ValueError：Dense应定义输入的最后一个维度。找到了None。

现在，我不知道我是否以预期的方式使用此数据集 API，或者是否有解决方法。

提前致谢！

编辑 1： 下面是我的模型，它在第一个密集层抛出错误

def conv_relu(input, kernel_shape):
    # Create variable named "weights".
    weights = tf.get_variable("weights", kernel_shape,
        initializer=tf.random_normal_initializer())
    # Create variable named "biases".
    biases = tf.get_variable("biases", kernel_shape[3],
        initializer=tf.constant_initializer(0.0))
    conv = tf.nn.conv2d(input, weights,
        strides=[1, 1, 1, 1], padding='VALID')
    return tf.nn.relu(conv + biases)

def fully(input, output_dim):
    assert len(input.get_shape())==2, 'Wrong input shape, need flattened tensor as input'
    input_dim = input.get_shape()[1]

    weight = tf.get_variable("weight", [input_dim, output_dim],
        initializer=tf.random_normal_initializer())
    bias = tf.get_variable('bias', [output_dim],
        initializer=tf.random_normal_initializer())

    fully = tf.nn.bias_add(tf.matmul(input, weight), bias)
    return fully


def simple_model(x):

    with tf.variable_scope('conv1'):
        conv1 = conv_relu(x, [3,3,1,10])
        conv1 = tf.nn.max_pool(conv1,[1,2,2,1],[1,2,2,1],'SAME')

    with tf.variable_scope('conv2'):
        conv2 = conv_relu(conv1, [3,3,10,10])
        conv2 = tf.nn.max_pool(conv2,[1,2,2,1],[1,2,2,1],'SAME')

    with tf.variable_scope('conv3'):
        conv3 = conv_relu(conv2, [3,3,10,10])
        conv3 = tf.nn.max_pool(conv3,[1,2,2,1],[1,2,2,1],'SAME')

    flat = tf.contrib.layers.flatten(conv3)
    with tf.variable_scope('fully1'):
        fully1 = tf.layers.dense(flat, 1000)
        fully1 = tf.nn.relu(fully1)

    with tf.variable_scope('fully2'):
        fully2 = tf.layers.dense(fully1, 100)
        fully2 = tf.nn.relu(fully2)

    with tf.variable_scope('output'):
        output = tf.layers.dense(fully2, 4)
        fully1 = tf.nn.relu(output)


    return output

编辑2：

在这里你可以看到张量的打印。注意 next_example 没有形状

next_example: Tensor("IteratorGetNext:0",
dtype =float32) next_label: Tensor("IteratorGetNext:1", shape=(?, 4), dtype=float32)

Answer 1

我自己找到了答案。

根据这一线索的简单的解决方法是刚刚设定的形状tf.Tensor.set_shape，如果你知道你的图像尺寸事前。

def input_parser(img_path, label):

    # read the img from file
    img_file = tf.read_file(img_path)
    img_decoded = tf.image.decode_image(img_file, channels=1)
    img_decoded = tf.image.convert_image_dtype(img_decoded, dtype=tf.float32)
    img_decoded.set_shape([90,160,1]) # This line was missing

    return img_decoded, label

如果 tensorflow 文档包含这一行，那就太好了。