使用theano和keras训练mnist数据集时出现断言错误

Question

我正在做一个关于深度学习的教程，有一个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])

然而，在线：

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，"用户代码未处理断言错误"。我没有收到其他信息。

欢迎任何帮助。非常感谢。

Answer 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])