TensorFlow网络在使用“dataset.map()之后接收到错误的张量形状`

以 https://www.tensorflow.org/guide/datasets#preprocessing_data_with_datasetmap tf.Dataset 它接受到图像的路径,并将其映射到图像张量。

def input_parser(image_path):

    image_data_string = tf.read_file(image_path)
    image_decoded = tf.image.decode_png(image_data_string, channels=3)
    image_float = tf.image.convert_image_dtype(image_decoded, dtype=tf.float32)
    return image_float


def train_model():

    image_paths = ['test_image1.png', .test_image2.png', 'test_image3.png']
    dataset = tf.data.Dataset.from_tensor_slices(image_paths)
    dataset = dataset.map(map_func=input_parser)
    iterator = dataset.make_initializable_iterator()
    input_images = iterator.get_next()

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        sess.run(iterator.initializer)
        for i in range(3):
            x = sess.run(input_images)
            print(x.shape)

这似乎工作正常,并打印出来:

(64, 64, 3)
(64, 64, 3)
(64, 64, 3)

所以我试着把这些数据输入网络进行训练,并相应地修改了代码:

def input_parser(image_path):

    image_data_string = tf.read_file(image_path)
    image_decoded = tf.image.decode_png(image_data_string, channels=3)
    image_float = tf.image.convert_image_dtype(image_decoded, dtype=tf.float32)
    return image_float


def train_model():

    image_paths = ['test_image1.png', .test_image2.png', 'test_image3.png']
    dataset = tf.data.Dataset.from_tensor_slices(image_paths)
    dataset = dataset.map(map_func=input_parser)
    iterator = dataset.make_initializable_iterator()
    input_images = iterator.get_next()

    x = tf.layers.conv2d(inputs=input_images, filters=50, kernel_size=[5, 5], name='layer1')
    x = tf.layers.flatten(x, name='layer2')
    prediction = tf.layers.dense(inputs=x, units=4, name='layer3')

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        sess.run(iterator.initializer)
        for i in range(3):
            p = sess.run(prediction)
            print(p)

然后,这给了我以下错误消息:

ValueError: Input 0 of layer layer1 is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: [None, None, 3]

我有两个问题:

1) 为什么我的网络接收到形状的输入 [None, None, 3] ,如我们所见,迭代器读取的数据是 [64, 64, 3]

2) 为什么输入的形状不是 [1, 64, 64, 3] ,即4维?我认为第一个维度应该是1,因为这是批大小(我不是在批处理数据,所以实际上这是一个1的批大小)。

谢谢!