如何解决Python中的“新数组的总大小必须不变错误”？

Question

我正在实现以下模型：

def ConnectomeCNNAutoencoder(input_shape, keep_pr=0.65, n_filter=32, n_dense1=64, n_classes=2, 
                      mode="autoencoder", sign="neg"):

input_1 = Input(shape=input_shape)
# Convolutional Encoder 
bias_init = tf.constant_initializer(value=0.001)
conv1 = Conv2D(filters=n_filter , kernel_size=(1,input_shape[1]), strides=(1, 1),
                                 padding= "valid", activation="selu", # "selu"
                                 kernel_initializer="glorot_uniform",
                                 bias_initializer=bias_init, name="conv1")(input_1)
dropout1 = Dropout(keep_pr, name="dropout1")(conv1)
conv2 = Conv2D(filters=n_filter*2 , kernel_size=(input_shape[1],1), strides=(1, 1),
                                 padding= "valid", activation="selu", 
                                 kernel_initializer="glorot_uniform",
                                 bias_initializer=bias_init, name="conv2")(dropout1)
encoded = Dropout(keep_pr, name="dropout2")(conv2)

# Classification
reshape = Reshape((n_filter*2,), name="reshape1")(encoded)
dense1 = Dense(n_dense1, activation="selu", name="dense1", kernel_regularizer=keras.regularizers.l1_l2())(reshape) 

if n_classes == 1:
    activation = "sigmoid"
else:
    activation = "softmax"
output = Dense(n_classes, activation=activation, name="output")(dense1)

# Decoder
dense2 = Dense(n_dense1, activation="selu", name="dense2")(output) 
dim_reconstruct = tuple(encoded.get_shape().as_list())
reshape2 = Reshape(dim_reconstruct[1:], name="reshape2")(dense2)

conv3 = Conv2DTranspose(filters=n_filter*2 , kernel_size=(1,1), strides=(1, 1),
                                  padding= "valid", activation="selu", # "selu"
                                  kernel_initializer="glorot_uniform",
                                  bias_initializer=bias_init, name="conv3")(reshape2)
conv4 = Conv2DTranspose(filters=n_filter , kernel_size=(input_shape[1],1), strides=(1, 1),
                                  padding= "valid", activation="selu", # "selu"
                                  kernel_initializer="glorot_uniform",
                                  bias_initializer=bias_init, name="conv4")(conv3)

if sign == "pos":
    reconstructed_activation = "sigmoid"
elif sign == "neg":
    reconstructed_activation = "tanh"
    
reconstructed_input = Conv2DTranspose(filters=input_shape[-1], kernel_size=(1,input_shape[1]), strides=(1, 1),
                                  padding= "valid", activation=reconstructed_activation, 
                                  kernel_initializer="glorot_uniform",
                                  bias_initializer=bias_init, name='autoencoder')(conv4)

if mode == "autoencoder":
    model = keras.models.Model(inputs=input_1, outputs=[output, reconstructed_input])
elif mode =="encoder":
    model = keras.models.Model(inputs=input_1, outputs=encoded)
elif mode == "decoder":
    model = keras.models.Model(inputs=input_1, outputs=reconstructed_input)
return model

模型在n_filter=32 和n_dense1=64 时工作正常，但是当我将这些变量更改为其他值时，会弹出此错误："ValueError: total size of new array must be unchanged"。 我知道这与reshape2中Reshape的使用有关，但我不知道如何解决。

我该如何解决这个问题？

谢谢！

Answer 1

问题出现在这一行：

reshape2 = Reshape(dim_reconstruct[1:], name="reshape2")(dense2)

张量dense2 的形状应该可以“转换”成dim_reconstruct[1:] 的形状。这意味着dim_reconstruct[1:]的值的乘积应该等于dense2的形状（不包括第零维-批量大小，因为keras在导出张量的维数时不计算它）。

如果n_filters = 30，dim_reconstruct[1:] 将是[1, 1, 60] - 因为您将n_filters 乘以2。但是密集过滤器的数量必须等于来自[1, 1, 60] 的值的乘积，即60。

我找不到任何将 1d 转换为 3d 数组的图像。但是有二维数组的例子：不能将数组 [1,2,3,4,5] 放入 2x3 二维数组，但可以将 [1,2,3,4,5,6] 转换为 [[1, 2, 3], [4, 5, 6]] 之类的东西

因此，您可以在调用ConnectomeCNNAutoencoder 时将n_units1 设置为60，或者您可以自动派生它：

    # Decoder
    dim_reconstruct = tuple(encoded.get_shape().as_list())  # say, (1, 1, 60)
    n_dense2 = np.product(dim_reconstruct[1:])  # will be 60
    dense2 = Dense(n_dense2, activation="selu", name="dense2")(output)
    reshape2 = Reshape(dim_reconstruct[1:], name="reshape2")(dense2)

完整示例（我删除了一些等于默认值的参数）：

import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import Input
from tensorflow.keras.layers import Conv2D, Dropout, Reshape, Dense, Conv2DTranspose


def ConnectomeCNNAutoencoder(input_shape,
                             keep_pr=0.65,
                             n_filter=32,
                             n_dense1=64,
                             n_classes=2,
                             mode="autoencoder",
                             sign="neg"):
    input_1 = Input(shape=input_shape)
    # Convolutional Encoder
    bias_init = tf.constant_initializer(value=0.001)
    conv1 = Conv2D(filters=n_filter,
                   kernel_size=(1, input_shape[1]),
                   strides=(1, 1),
                   activation="selu",  # "selu"
                   bias_initializer=bias_init,
                   name="conv1")(input_1)
    dropout1 = Dropout(keep_pr, name="dropout1")(conv1)
    conv2 = Conv2D(filters=n_filter * 2,
                   kernel_size=(input_shape[1], 1),
                   strides=(1, 1),
                   activation="selu",
                   bias_initializer=bias_init,
                   name="conv2")(dropout1)
    encoded = Dropout(keep_pr, name="dropout2")(conv2)

    # Classification
    reshape = Reshape((n_filter * 2,), name="reshape1")(encoded)
    dense1 = Dense(n_dense1,
                   activation="selu",
                   name="dense1",
                   kernel_regularizer=keras.regularizers.l1_l2())(reshape)

    if n_classes == 1:
        activation = "sigmoid"
    else:
        activation = "softmax"

    output = Dense(n_classes, activation=activation, name="output")(dense1)

    # Decoder - Changes here
    dim_reconstruct = tuple(encoded.get_shape().as_list())
    n_dense2 = np.product(dim_reconstruct[1:])
    dense2 = Dense(n_dense2, activation="selu", name="dense2")(output)
    reshape2 = Reshape(dim_reconstruct[1:], name="reshape2")(dense2)

    conv3 = Conv2DTranspose(filters=n_filter * 2,
                            kernel_size=(1, 1),
                            strides=(1, 1),
                            activation="selu",  # "selu"
                            bias_initializer=bias_init,
                            name="conv3")(reshape2)
    conv4 = Conv2DTranspose(filters=n_filter,
                            kernel_size=(input_shape[1], 1),
                            strides=(1, 1),
                            activation="selu",  # "selu"
                            bias_initializer=bias_init,
                            name="conv4")(conv3)

    if sign == "pos":
        reconstructed_activation = "sigmoid"
    elif sign == "neg":
        reconstructed_activation = "tanh"

    reconstructed_input = Conv2DTranspose(filters=input_shape[-1],
                                          kernel_size=(1, input_shape[1]),
                                          strides=(1, 1),
                                          activation=reconstructed_activation,
                                          bias_initializer=bias_init,
                                          name='autoencoder')(conv4)

    if mode == "autoencoder":
        model = keras.models.Model(inputs=input_1, outputs=[output, reconstructed_input])
    elif mode == "encoder":
        model = keras.models.Model(inputs=input_1, outputs=encoded)
    elif mode == "decoder":
        model = keras.models.Model(inputs=input_1, outputs=reconstructed_input)
    else:
        raise ValueError("Unexpected mode: %s" % mode)
    return model


model = ConnectomeCNNAutoencoder((32, 32, 3), n_filter=30, n_dense1=65)