检查输入时出错：预期 flatten_input 有 3 个维度，但得到了形状为 (None, 100, 100, 1) 的数组

Posted 2023-03-13

【中文标题】检查输入时出错：预期 flatten_input 有 3 个维度，但得到了形状为 (None, 100, 100, 1) 的数组

【英文标题】：Error when checking input: expected flatten_input to have 3 dimensions, but got array with shape (None, 100, 100, 1)

【发布时间】：2019-02-25 16:46:42

【问题描述】：

使用TensorFlow/Keras，我想将图片分为自拍和非自拍两类。

我已将样本收集到两个文件系统文件夹中，每个类别一个。

在使用从文件系统加载图片后，我按照 MNIST 时尚的官方教程（这也是一个图片分类问题）实施了下面的训练，如 https://***.com/a/52417770/226958 所示。

很遗憾，我收到一个错误：

1.10.1
Tensor("IteratorGetNext:0", shape=(?, 100, 100, 1), dtype=float32)
Tensor("IteratorGetNext:1", shape=(?,), dtype=int32)
Traceback (most recent call last):
  File "run.py", line 50, in <module>
    model.fit(images, labels, epochs=1, steps_per_epoch=60000)
  File "/home/nico/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/training.py", line 1278, in fit
    validation_split=validation_split)
  File "/home/nico/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/training.py", line 878, in _standardize_user_data
    exception_prefix='input')
  File "/home/nico/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/training_utils.py", line 182, in standardize_input_data
    'with shape ' + str(data_shape))
ValueError: Error when checking input: expected flatten_input to have 3 dimensions, but got array with shape (None, 100, 100, 1)

这里是源代码：

import tensorflow as tf
print(tf.__version__)

out_shape = tf.convert_to_tensor([100, 100])
batch_size = 2

image_paths, labels = ["selfies-data/1", "selfies-data/2"], [1, 2]
epoch_size = len(image_paths)
image_paths = tf.convert_to_tensor(image_paths, dtype=tf.string)
labels = tf.convert_to_tensor(labels)

# The images loading part is from https://***.com/a/52417770/226958
dataset = tf.data.Dataset.from_tensor_slices((image_paths, labels))
dataset = dataset.repeat().shuffle(epoch_size)

def map_fn(path, label):
    # path/label represent values for a single example
    image = tf.image.decode_jpeg(tf.read_file(path))

    # some mapping to constant size - be careful with distorting aspec ratios
    image = tf.image.resize_images(image, out_shape)
    image = tf.image.rgb_to_grayscale(image)
    # color normalization - just an example
    image = tf.to_float(image) * (2. / 255) - 1
    return image, label

# num_parallel_calls > 1 induces intra-batch shuffling
dataset = dataset.map(map_fn, num_parallel_calls=8)
dataset = dataset.batch(batch_size)
dataset = dataset.prefetch(1)

images, labels = dataset.make_one_shot_iterator().get_next()

# All of the following is from https://www.tensorflow.org/tutorials/keras/basic_classification
from tensorflow import keras

model = keras.Sequential([
    keras.layers.Flatten(input_shape=(100, 100)),
    keras.layers.Dense(128, activation=tf.nn.relu),
    keras.layers.Dense(10, activation=tf.nn.softmax)
])

model.compile(optimizer=tf.train.AdamOptimizer(),
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

print(images)
print(labels)
model.fit(images, labels, epochs=epoch_size, steps_per_epoch=60000)

虽然我已阅读过类似的问题，但我没有看到与此 None 相关的任何问题。

如何使 Keras 适应我的输入，或转换我的输入以使 Keras 接受它？

【参考方案1】：

1) 图像有一个通道，因此这必须反映在输入形状参数中：

keras.layers.Flatten(input_shape=(100, 100, 1))

2) 要使用tf.data API 加载文件，您需要先获取图像文件名及其对应的标签：

image_paths, lbls = ["selfies-data/1", "selfies-data/2"], [0., 1.]

labels = []
file_names = []
for d, l in zip(image_paths, lbls):
    # get the list all the images file names
    name = [os.path.join(d,f) for f in os.listdir(d)]
    file_names.extend(name)
    labels.extend([l] * len(name))

file_names = tf.convert_to_tensor(file_names, dtype=tf.string)
labels = tf.convert_to_tensor(labels)

dataset = tf.data.Dataset.from_tensor_slices((file_names, labels))

# the rest is the same 

您可能还需要扩展labels 的维度，使其具有(?, 1) 的形状（而不是(?,)）。为此，您可以在map_fn 函数中加入以下行：

labels = tf.expand_dims(labels, axis=-1)

3) 如果你有两个类，那么为什么最后一层有 10 个单元？这是一个二元分类问题，所以让最后一层有一个带有sigmoid 激活的单元。最后把loss改成binary_crossentropy：

       # ... 
       keras.layers.Dense(1, activation=tf.nn.sigmoid)
])

model.compile(optimizer=tf.train.AdamOptimizer(),
              loss='binary_crossentropy',
              metrics=['accuracy'])

【讨论】：

非常感谢，感谢您的提示，我取得了巨大的进步！