Python中的"total size of new array must be unchanged error"怎么解？
How to solve "total size of new array must be unchanged error" in Python?
我正在实施以下模型：
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这个问题。
我该如何解决这个问题？
谢谢！
问题出现在这一行：
reshape2 = Reshape(dim_reconstruct[1:], name="reshape2")(dense2)
张量 dense2 的形状应该 'transformed' 变成 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 在推导张量的维度时不计算它） .
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值的乘积来自 [1, 1, 60]，即 60.
我找不到任何将 1d 转换为 3d 数组的图像。但是有一个二维数组的例子：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]]
因此，您可以在调用 ConnectomeCNNAutoencoder 时将 n_units1 设置为 60，或者您可以改为自动导出它：
# 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)
我正在实施以下模型：
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这个问题。
我该如何解决这个问题？
谢谢！
问题出现在这一行：
reshape2 = Reshape(dim_reconstruct[1:], name="reshape2")(dense2)
张量 dense2 的形状应该 'transformed' 变成 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 在推导张量的维度时不计算它） .
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值的乘积来自 [1, 1, 60]，即 60.
我找不到任何将 1d 转换为 3d 数组的图像。但是有一个二维数组的例子：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]]
因此，您可以在调用 ConnectomeCNNAutoencoder 时将 n_units1 设置为 60，或者您可以改为自动导出它：
# 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)