使用 theano 和 keras 训练 mnist 数据集时出现 AssertionError答案

【问题标题】：AssertionError while training mnist dataset using theano and keras使用 theano 和 keras 训练 mnist 数据集时出现 AssertionError
【发布时间】：2016-07-17 08:32:11
【问题描述】：

我在做深度学习的教程，里面有mnist数据集分类示例：

import matplotlib.pyplot as plt
import numpy as np

np.random.seed(123)

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.utils import np_utils

batch_size = 128
nb_classes = 10 # number of classes

# input image dimensions
img_rows, img_cols = 28, 28

(X_train, y_train) , (X_test, y_test) = mnist.load_data()

# reshape data
X_train =  X_train.reshape(X_train.shape[0], 1, img_rows, img_cols) # 1 is 1 channnel i.e. grayscale
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)

X_train = X_train.astype("float32")
X_test = X_test.astype("float32")

# normalization
X_train /= 255;
X_test /= 255;

print("X_train shape: ", X_train.shape)
print(X_train.shape[0], " train samples")
print(X_test.shape[0], " test samples")

# convert class vectors to binary class matrices

y_train = np_utils.to_categorical(y_train, nb_classes)
y_test = np_utils.to_categorical(y_train, nb_classes)
print("One hot encoding: {}".format(y_train[0, :]))

model = Sequential();

model.add(Convolution2D(6, 5, 5, input_shape = (1, img_rows, img_cols), border_mode = "same"))

model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(16, 5, 5, border_mode= "same"))

model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(120, 5, 5, border_mode= "same"))

model.add(Activation("relu"))
model.add(Dropout(0.25))

model.add(Flatten())

model.add(Dense(84))
model.add(Activation("relu"))
model.add(Dropout(0.5))
model.add(Dense(10)) # because 10 output classes
model.add(Activation("softmax"))

# TRAIN
model.compile(loss = "categorical_crossentropy", optimizer="adadelta")
nb_epoch = 2

model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epoch, show_accuracy= True, verbose = 1, validation_data = (X_test, y_test))
score = model.evaluate(X_test, y_test, show_accuracy = True, verbose = 0)
print("Test score: ", score[0])
print("Test accuracy: ", score[1])

不过，就行了：

model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epoch, show_accuracy= True, verbose = 1, validation_data = (X_test, y_test))

我得到一个异常，“AssertionError 未被用户代码处理”。我在异常中没有收到其他消息。

欢迎任何帮助。谢谢。

【问题讨论】：

不知何故您没有正确收到错误消息。但这行y_test = np_utils.to_categorical(y_train, nb_classes) 显然是错误的。
是的，这就是问题所在。谢谢，现在可以了:)
@y300：你能把它作为答案发布吗？

标签： python theano deep-learning keras

【解决方案1】：

正确的代码应该是：

import matplotlib.pyplot as plt
import numpy as np

np.random.seed(123)

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.utils import np_utils

batch_size = 128
nb_classes = 10 # number of classes

# input image dimensions
img_rows, img_cols = 28, 28

(X_train, y_train) , (X_test, y_test) = mnist.load_data()

# reshape data
X_train =  X_train.reshape(X_train.shape[0], 1, img_rows, img_cols) # 1 is 1 channnel i.e. grayscale
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)

X_train = X_train.astype("float32")
X_test = X_test.astype("float32")

# normalization
X_train /= 255;
X_test /= 255;

print("X_train shape: ", X_train.shape)
print(X_train.shape[0], " train samples")
print(X_test.shape[0], " test samples")

# convert class vectors to binary class matrices

y_train = np_utils.to_categorical(y_train, nb_classes)
y_test = np_utils.to_categorical(y_test, nb_classes)
print("One hot encoding: {}".format(y_train[0, :]))

model = Sequential();

model.add(Convolution2D(6, 5, 5, input_shape = (1, img_rows, img_cols), border_mode = "same"))

model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(16, 5, 5, border_mode= "same"))

model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(120, 5, 5, border_mode= "same"))

model.add(Activation("relu"))
model.add(Dropout(0.25))

model.add(Flatten())

model.add(Dense(84))
model.add(Activation("relu"))
model.add(Dropout(0.5))
model.add(Dense(10)) # because 10 output classes
model.add(Activation("softmax"))

# TRAIN
model.compile(loss = "categorical_crossentropy", optimizer="adadelta")
nb_epoch = 2

model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epoch, show_accuracy= True, verbose = 1, validation_data = (X_test, y_test))
score = model.evaluate(X_test, y_test, show_accuracy = True, verbose = 0)
print("Test score: ", score[0])
print("Test accuracy: ", score[1])

【讨论】：