Question

我正在使用GAN教程中的代码在Tensorflow中生成MNIST数字。

（此处链接：https://www.tensorflow.org/beta/tutorials/generative/dcgan）

我知道了

Traceback (most recent call last):
  File "GAN_MNIST_tutorial.py", line 66, in <module>
    plt.imshow(np.array(generated_image[0, :, :, 0]), cmap='gray')
  File "C:\venv\lib\site-packages\matplotlib\pyplot.py", line 2677, in imshow
    None else {}), **kwargs)
  File "C:\venv\lib\site-packages\matplotlib\__init__.py", line 1589, in inner
    return func(ax, *map(sanitize_sequence, args), **kwargs)
  File "C:\venv\lib\site-packages\matplotlib\cbook\deprecation.py", line 369, in wrapper
    return func(*args, **kwargs)
  File "C:\venv\lib\site-packages\matplotlib\cbook\deprecation.py", line 369, in wrapper
    return func(*args, **kwargs)
  File "C:\venv\lib\site-packages\matplotlib\axes\_axes.py", line 5660, in imshow
    im.set_data(X)
  File "C:\venv\lib\site-packages\matplotlib\image.py", line 678, in set_data
    "float".format(self._A.dtype))
TypeError: Image data of dtype object cannot be converted to float

当我运行它时。

这是我的代码：

from __future__ import absolute_import, division, print_function, unicode_literals

import tensorflow as tf 
tf.__version__

import glob
import imageio
import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
from tensorflow.keras import layers
import time

def make_generator_model():
    model = tf.keras.Sequential()
    model.add(layers.Dense(7*7*256, use_bias=False, input_shape=(100,)))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())
    model.add(layers.Reshape((7, 7, 256)))

    assert model.output_shape == (None, 7, 7, 256) # Note: None is the batch size

    model.add(layers.Conv2DTranspose(128, (5, 5), strides=(1, 1), padding='same', use_bias=False))
    assert model.output_shape == (None, 7, 7, 128)

    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same', use_bias=False))
    assert model.output_shape == (None, 14, 14, 64)

    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2DTranspose(1, (5, 5), strides=(2, 2), padding='same', use_bias=False, activation='tanh'))
    assert model.output_shape == (None, 28, 28, 1)

    return model

generator = make_generator_model()

noise = tf.random.normal([1, 100])

generated_image = generator(noise, training=False)

plt.imshow(generated_image[0, :, :, 0], cmap='gray')

我尝试在dtype = 'float32中添加generated_image，并将generated_image转换为一个numpy数组，但无济于事。有什么问题吗？

Answer 1

我认为您使用tensorflow 1.x运行了代码。在TF1.x（未启用急切功能）中，操作（Ops）生成符号张量，其中不包含任何值，除非您在会话中运行这些张量。该会话将执行这些图模式符号张量并返回实际张量（可以从张量访问numpy数组）。

因此，我在代码的末尾添加了几行以执行这些符号张量。请检查下面的代码。如果您还有其他问题，请告诉我。

from __future__ import absolute_import, division, print_function, unicode_literals

import tensorflow as tf 
tf.__version__

import glob
import imageio
import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
from tensorflow.keras import layers
import time

def make_generator_model():
    model = tf.keras.Sequential()
    model.add(layers.Dense(7*7*256, use_bias=False, input_shape=(100,)))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())
    model.add(layers.Reshape((7, 7, 256)))

    assert model.output_shape == (None, 7, 7, 256) # Note: None is the batch size

    model.add(layers.Conv2DTranspose(128, (5, 5), strides=(1, 1), padding='same', use_bias=False))
    assert model.output_shape == (None, 7, 7, 128)

    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same', use_bias=False))
    assert model.output_shape == (None, 14, 14, 64)

    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2DTranspose(1, (5, 5), strides=(2, 2), padding='same', use_bias=False, activation='tanh'))
    assert model.output_shape == (None, 28, 28, 1)

    return model

generator = make_generator_model()

noise = tf.random.normal([1, 100])
generated_image = generator(noise, training=False)

with tf.Session() as sess:
  sess.run(tf.global_variables_initializer())
  generated_image = sess.run(generated_image)
plt.imshow(generated_image[0, :, :, 0], cmap='gray')

如果您认为此答案有用，请接受此答案和/或对其进行投票。谢谢！

Answer 2

问题是您将符号keras / tensorflow函数与数字函数（例如matplotlib）混合在一起。

如果要生成随机向量并进行模型预测，则应使用：

noise = np.random.normal(size=(1, 100))
generated_image = generator.predict(noise)
plt.imshow(generated_image[0, :, :, 0], cmap='gray')

Answer 3

通过从TF1升级到TF2解决了此问题。我在tf1.14.X上运行了它，但在升级到tf 2.0之后代码无法正常工作。

TypeError：dtype对象的图像数据无法转换为float

3 个答案: