Question

我正在学习一本深度学习书中的示例（使用keras ch1进行反学习）这就是我所关注的例子

from __future__ import print_function
import numpy as np
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD
from keras.utils import np_utils

import matplotlib.pyplot as plt

np.random.seed(1671)  # for reproducibility

# network and training
NB_EPOCH = 250
BATCH_SIZE = 128
VERBOSE = 1
NB_CLASSES = 10   # number of outputs = number of digits
OPTIMIZER = SGD() # optimizer, explained later in this chapter
N_HIDDEN = 128
VALIDATION_SPLIT=0.2 # how much TRAIN is reserved for VALIDATION
DROPOUT = 0.3

# data: shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()

#X_train is 60000 rows of 28x28 values --> reshaped in 60000 x 784
RESHAPED = 784
#
X_train = X_train.reshape(60000, RESHAPED)
X_test = X_test.reshape(10000, RESHAPED)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')

# normalize 
X_train /= 255
X_test /= 255
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)

# M_HIDDEN hidden layers
# 10 outputs
# final stage is softmax

model = Sequential()
model.add(Dense(N_HIDDEN, input_shape=(RESHAPED,)))
model.add(Activation('relu'))
model.add(Dropout(DROPOUT))
model.add(Dense(N_HIDDEN))
model.add(Activation('relu'))
model.add(Dropout(DROPOUT))
model.add(Dense(NB_CLASSES))
model.add(Activation('softmax'))
model.summary()

model.compile(loss='categorical_crossentropy',
              optimizer=OPTIMIZER,
              metrics=['accuracy'])

history = model.fit(X_train, Y_train,
                    batch_size=BATCH_SIZE, epochs=NB_EPOCH,
                    verbose=VERBOSE, validation_split=VALIDATION_SPLIT)

score = model.evaluate(X_test, Y_test, verbose=VERBOSE)

print("\nTest score:", score[0])
print('Test accuracy:', score[1])

# list all data in history
print(history.history.keys())

# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

如果将此示例粘贴到https://colab.research.google.com中，则精度为0.9779

但是我在colab中写了相同的示例（相同的模型，参数，种子），我的精度约为0.6755。对于相同的模型，相同的参数结果应该不会有太大变化。但是我找不到我错过的东西

我也尝试逐行检查，但仍然无法弄清楚我在代码示例中错过了什么，从而使精度降低了。

这是我在colab中编写的代码：

https://github.com/anandvimal/deeplearning-experiments/blob/master/mnist_keras_1_2.ipynb

Answer 1

我刚刚阅读了您的笔记本，发现您执行了两次标准化单元操作，从而导致不良结果。

# normalize 
X_train /= 255
X_test /= 255
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')

使用相同的代码在深度学习模型中获得不同的准确性

1 个答案: