ValueError：检查目标时出错：预期 up_sampling2d_2 有 4 个维度，但得到了形状为 (128, 1) 的数组

Question

我正在尝试使用自定义数据生成器训练一个堆叠卷积自动编码器，因为它是我生成的一个非常大的合成数据集。我已经按照 https://medium.com/@mrgarg.rajat/training-on-large-datasets-that-dont-fit-in-memory-in-keras-60a974785d71 教程进行操作，但仍然无法正常工作

我的数据集目录是这样的：

real_train
   - img 1.png
   - img 2.png
   - ....

这是我的 My_Data_Generator 类

class My_Data_Generator(keras.utils.Sequence):

    def __init__(self, image_filenames, labels, batch_size):
        self.image_filenames = image_filenames
        self.labels =  labels
        self.batch_size = batch_size
        self.n = 0

    def __next__(self):
        # Get one batch of data
        data = self.__getitem__(self.n)
        # Batch index
        self.n += 1
        # If we have processed the entire dataset then
        if self.n >= self.__len__():
            self.on_epoch_end
            self.n = 0

        return data

    def __len__(self) :
        return (np.ceil(len(self.image_filenames) / float(self.batch_size))).astype(np.int)

    def __getitem__(self, idx):
        batch_x = self.image_filenames[idx * self.batch_size:(idx + 1) * self.batch_size]
        batch_y = self.labels[idx * self.batch_size:(idx + 1) * self.batch_size]

        return np.array([
            resize(imread('E:/FontRecognition/Dataset_Final/preprocessed/real_train/' + str(file_name)), (105,105,1)) 
                for file_name in batch_x])/255.0, np.array(batch_y)

这是我的代码

# load
X_train = np.load('X_train_filenames.npy')
X_val = np.load('X_val_filenames.npy')

# print(X_train.shape)
# print(X_val.shape)

batch_size = 128

my_training_batch_generator = My_Data_Generator(X_train, X_train, batch_size=batch_size)
my_validation_batch_generator = My_Data_Generator(X_val, X_val, batch_size=batch_size)

images, labels = next(my_training_batch_generator)
print("Train")
print(images.shape)
print(labels.shape)
images, labels = next(my_validation_batch_generator)
print("Val")
print(images.shape)
print(labels.shape)

input_img = Input(shape=(105,105,1))

x = Conv2D(64, kernel_size=(48,48), activation='relu', padding='same', strides=1)(input_img)
x = BatchNormalization()(x)
x = MaxPooling2D(pool_size=(2,2)) (x)
x = Conv2D(128, kernel_size=(24,24), activation='relu', padding='same', strides=1)(x)
x = BatchNormalization()(x)
encoded = MaxPooling2D(pool_size=(2,2))(x)

x = Conv2D(64, kernel_size=(24,24), activation='relu', padding='same', strides=1)(encoded)
x = UpSampling2D(size=(2,2))(x)
x = Conv2D(1, kernel_size=(48,48), activation='relu', padding='same', strides=1)(x)
decoded = UpSampling2D(size=(2,2))(x)

adam = keras.optimizers.Adam(lr=0.01)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer=adam, loss='mean_squared_error')

autoencoder.summary()

num_epochs = 20
autoencoder.fit_generator(generator=my_training_batch_generator,
                    steps_per_epoch=(int(1836695 // batch_size)),
                    epochs=num_epochs,
                    verbose=1,
                    validation_data=my_validation_batch_generator,
                    validation_steps=(int(459174 // batch_size))
                    # use_multiprocessing=True,
                    # workers=6
                    )
print("Finished")

我尝试运行代码，输出如下：

Model: "model_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
input_1 (InputLayer)         (None, 105, 105, 1)       0
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 105, 105, 64)      147520
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 52, 52, 64)        0
_________________________________________________________________
batch_normalization_1 (Batch (None, 52, 52, 64)        256       
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 52, 52, 128)       4718720
_________________________________________________________________
batch_normalization_2 (Batch (None, 52, 52, 128)       512
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 26, 26, 128)       0
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 26, 26, 64)        4718656
_________________________________________________________________
up_sampling2d_1 (UpSampling2 (None, 52, 52, 64)        0
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 52, 52, 1)         147457
_________________________________________________________________
up_sampling2d_2 (UpSampling2 (None, 104, 104, 1)       0
=================================================================
Total params: 9,733,121
Trainable params: 9,732,737
Non-trainable params: 384
_________________________________________________________________
Epoch 1/20
Traceback (most recent call last):
  File "SCAE_train.py", line 142, in <module>
    validation_steps=(int(459174 // batch_size))
  File "C:\MyProgramFiles\Anaconda3\envs\tf_gpu\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "C:\MyProgramFiles\Anaconda3\envs\tf_gpu\lib\site-packages\keras\engine\training.py", line 1732, in fit_generator
    initial_epoch=initial_epoch)
  File "C:\MyProgramFiles\Anaconda3\envs\tf_gpu\lib\site-packages\keras\engine\training_generator.py", line 221, in fit_generator
    reset_metrics=False)
  File "C:\MyProgramFiles\Anaconda3\envs\tf_gpu\lib\site-packages\keras\engine\training.py", line 1508, in train_on_batch
    class_weight=class_weight)
  File "C:\MyProgramFiles\Anaconda3\envs\tf_gpu\lib\site-packages\keras\engine\training.py", line 621, in _standardize_user_data
    exception_prefix='target')
  File "C:\MyProgramFiles\Anaconda3\envs\tf_gpu\lib\site-packages\keras\engine\training_utils.py", line 135, in standardize_input_data
    'with shape ' + str(data_shape))
ValueError: Error when checking target: expected up_sampling2d_2 to have 4 dimensions, but got array with shape (128, 1)

我是 keras 和 python 的新手，但我仍然不知道是什么原因造成的..

Answer 1

首先，你的模型的输入输出形状不匹配。您的模型输入尺寸为 105x105，而您的输出尺寸为 104x104。要么使用类似的输入大小，要么调整卷积层中的内核/步幅大小。

但要回答您的问题，请注意您关注的 tutorial 执行分类，因此使用 (batch_size, number_of_categories) 的目标形状。但是，您正在使用自动编码器，这意味着您应该更改数据生成器以返回适当的目标，即 (batch_size, HEIGHT, WIDTH, NUM_CHANNELS) 的形状与您的输入相同。

您的输入和输出图像是相同的，因此您不需要在数据生成器中添加额外的 labels 参数，只需读取图像并返回它们的两个副本即可。假设您的图像文件格式/目录正确，我已编辑您的代码以如下方式工作：

您的数据生成器：

class My_Custom_Generator(keras.utils.Sequence) :

  def __init__(self, image_filenames, batch_size) :
    self.image_filenames = image_filenames
    self.batch_size = batch_size


  def __len__(self) :
    return (np.ceil(len(self.image_filenames) / float(self.batch_size))).astype(np.int)


  def __getitem__(self, idx) :
    batch_x = self.image_filenames[idx * self.batch_size : (idx+1) * self.batch_size]

    current_x = np.array(
            resize(imread('E:/FontRecognition/Dataset_Final/preprocessed/real_train/' + str(file_name)), (105,105,1)) 
                for file_name in batch_x])/255.0
    return current_x, current_x

您的模型和脚本：

# load
X_train = np.load('X_train_filenames.npy')
X_val = np.load('X_val_filenames.npy')

# print(X_train.shape)
# print(X_val.shape)

batch_size = 128

my_training_batch_generator = My_Data_Generator(X_train, batch_size=batch_size)
my_validation_batch_generator = My_Data_Generator(X_val, batch_size=batch_size)


input_img = keras.layers.Input(shape=(104,104,1))

x = keras.layers.Conv2D(64, kernel_size=(48,48), activation='relu', padding='same', strides=1)(input_img)
x = keras.layers.BatchNormalization()(x)
x = keras.layers.MaxPooling2D(pool_size=(2,2), padding='same') (x)
x = keras.layers.Conv2D(128, kernel_size=(24,24), activation='relu', padding='same', strides=1)(x)
x = keras.layers.BatchNormalization()(x)
encoded = keras.layers.MaxPooling2D(pool_size=(2,2))(x)

x = keras.layers.Conv2D(64, kernel_size=(24,24), activation='relu', padding='same', strides=1)(encoded)
x = keras.layers.UpSampling2D(size=(2,2))(x)
x = keras.layers.Conv2D(1, kernel_size=(48,48), activation='relu', padding='same', strides=1)(x)
decoded = keras.layers.UpSampling2D(size=(2,2))(x)
autoencoder = keras.Model(input_img, decoded)
autoencoder.summary()
adam = keras.optimizers.Adam(lr=0.01)
autoencoder.compile(optimizer=adam, loss='mean_squared_error')
num_epochs = 20
autoencoder.fit_generator(generator=my_training_batch_generator,
                    epochs=num_epochs,
                    verbose=1,
                    validation_data=my_validation_batch_generator
                    # use_multiprocessing=True,
                    # workers=6
                    )

请注意，我已经删除了 steps_per_epoch 和 validation_steps 参数，因为继承 keras.utils.Sequence 的自定义数据生成器不需要它们并且可以直接从数据中推断出来。