0

我有一个从文件tf.data.Dataset中读取的tfrecords文件,如下所示:

import tensorflow as tf

# given an existing record_file

raw_dataset = tf.data.TFRecordDataset(record_file)
example_description = {
        "height": tf.io.FixedLenFeature([], tf.int64),
        "width": tf.io.FixedLenFeature([], tf.int64),
        "channels": tf.io.FixedLenFeature([], tf.int64),
        "image": tf.io.FixedLenFeature([], tf.string),
    }
dataset = raw_dataset.map(
    lambda example: tf.io.parse_single_example(example, example_description)
)

接下来,我将这些特征组合成一个图像,如下所示:

dataset = dataset.map(_extract_image_from_sample)

# and

def _extract_image_from_sample(sample):
    height = tf.cast(sample["height"], tf.int32) # always 1038
    width = tf.cast(sample["width"], tf.int32) # always 1366
    depth = tf.cast(sample["channels"], tf.int32) # always 3
    shape = [height, width, depth]

    image = sample["image"]
    image = decode_tf_image(image)
    image = tf.reshape(image, shape)

    return image

此时,数据集中的任何图像都有形状(None, None, None)(这让我感到惊讶,因为我重塑了它们)。当我尝试使用以下方法扩充数据集时,我认为这是导致错误的原因tf.keras.preprocessing.image.ImageDataGenerator

augmented_dataset = dataset.map(random_image_augmentation)

# and

image_data_generator = tf.keras.preprocessing.image.ImageDataGenerator(
    rotation_range=45,
    width_shift_range=0.1,
    height_shift_range=0.1,
    shear_range=5.0,
    zoom_range=[0.9, 1.2],
    fill_mode="reflect",
    horizontal_flip=True,
    vertical_flip=True,
)

def random_image_augmentation(image: tf.Tensor) -> tf.Tensor:
    transform = image_data_generator.get_random_transform(img_shape=image.shape)
    image = image_data_generator.apply_transform(image, transform)
    return image

这会导致错误消息:

TypeError: in user code:
    # ...
    C:\Users\[PATH_TO_ENVIRONMENT]\lib\site-packages\keras_preprocessing\image\image_data_generator.py:778 get_random_transform  *
        tx *= img_shape[img_row_axis]

    TypeError: unsupported operand type(s) for *=: 'float' and 'NoneType'

但是,如果我不使用图形模式,而是使用渴望模式,这就像一个魅力:

it = iter(dataset)
for i in range(3):
    image = it.next()
    image = random_image_augmentation(image.numpy())

这使我得出结论,主要错误是读取数据集后缺少形状信息。但我不知道如何比我已经做的更明确地定义它。有任何想法吗?

4

1 回答 1

0

用于tf.py_function包装要求张量具有如下形状的预处理函数:

augmented_dataset = dataset.map(
    lambda x: tf.py_function(random_image_augmentation, inp=[x], Tout=tf.float32),
    num_parallel_calls=tf.data.experimental.AUTOTUNE
)

# and

def random_image_augmentation(image: tf.Tensor) -> tf.Tensor:
    image = image.numpy()  # now we can do this, because tensors have this function in eager mode
    transform = image_data_generator.get_random_transform(img_shape=image.shape)
    image = image_data_generator.apply_transform(image, transform)
    return image

这对我有用,但我不确定它是否是唯一甚至最好的解决方案。

于 2021-02-01T12:43:15.253 回答