keras下解决 example 案例中 MNIST 数据集下载不了的问题

keras 源码中下载MNIST的方式是 path = get_file(path, origin='https://s3.amazonaws.com/img-datasets/mnist.npz')，数据源是通过 url = https://s3.amazonaws.com/img-datasets/mnist.npz 进行下载的。访问该 url 地址被墙了，导致 MNIST 相关的案例都卡在数据下载的环节。本文主要提供解决方案，让需要的读者可以跑案例的代码感受一下。

下载 mnist.npz 数据集

本文使用的 mnist.npz 数据集是通过一个 japan 的服务器下载得到的，在此免费分享给大家。如果下载有问题的话，可以留言哈。

下载链接：https://pan.baidu.com/s/1jH6uFFC密码: dw3d

下载后文件放在*.py所在目录下

改造原来的文件

#load data

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

import numpy as np

path='./mnist.npz'

f = np.load(path)

X_train, y_train = f['x_train'], f['y_train']

X_test, y_test = f['x_test'], f['y_test']

f.close()

运行效果如下所示：

45568/48000 [===========================>..] - ETA: 4s - loss: 0.0574 - acc: 0.9818

45696/48000 [===========================>..] - ETA: 4s - loss: 0.0576 - acc: 0.9817

45824/48000 [===========================>..] - ETA: 4s - loss: 0.0576 - acc: 0.9817

45952/48000 [===========================>..] - ETA: 3s - loss: 0.0576 - acc: 0.9817

46080/48000 [===========================>..] - ETA: 3s - loss: 0.0576 - acc: 0.9817

46208/48000 [===========================>..] - ETA: 3s - loss: 0.0577 - acc: 0.9817

46336/48000 [===========================>..] - ETA: 3s - loss: 0.0576 - acc: 0.9817

46464/48000 [============================>.] - ETA: 2s - loss: 0.0578 - acc: 0.9817

46592/48000 [============================>.] - ETA: 2s - loss: 0.0577 - acc: 0.9817

46720/48000 [============================>.] - ETA: 2s - loss: 0.0578 - acc: 0.9817

46848/48000 [============================>.] - ETA: 2s - loss: 0.0578 - acc: 0.9817

46976/48000 [============================>.] - ETA: 1s - loss: 0.0579 - acc: 0.9817

47104/48000 [============================>.] - ETA: 1s - loss: 0.0580 - acc: 0.9816

47232/48000 [============================>.] - ETA: 1s - loss: 0.0580 - acc: 0.9816

47360/48000 [============================>.] - ETA: 1s - loss: 0.0580 - acc: 0.9817

47488/48000 [============================>.] - ETA: 0s - loss: 0.0579 - acc: 0.9817

47616/48000 [============================>.] - ETA: 0s - loss: 0.0578 - acc: 0.9817

47744/48000 [============================>.] - ETA: 0s - loss: 0.0578 - acc: 0.9817

47872/48000 [============================>.] - ETA: 0s - loss: 0.0577 - acc: 0.9818

48000/48000 [==============================] - 100s 2ms/step - loss: 0.0577 - acc: 0.9817 - val_loss: 0.0447 - val_acc: 0.9862

Test score: 0.03886812744811614

Test accuracy: 0.9869

---

完整代码如下：

# -*- coding: utf-8 -*-

__author__ = "TF大Q"

import numpy as np

np.random.seed(1337)

from keras.datasets import mnist

from keras.models import Sequential

from keras.layers import Dense, Dropout, Activation, Flatten

from keras.layers import Convolution2D, MaxPooling2D

from keras.utils import np_utils

from keras import backend as K

# 全局变量

batch_size = 128

nb_classes = 10

epochs = 5

# input image dimensions

img_rows, img_cols = 28, 28

# 卷积滤波器的数量

nb_filters = 32

# size of pooling area for max pooling

pool_size = (2, 2)

# convolution kernel size

kernel_size = (3, 3)

#load data

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

import numpy as np

path='./mnist.npz'

f = np.load(path)

X_train, y_train = f['x_train'], f['y_train']

X_test, y_test = f['x_test'], f['y_test']

f.close()

#from sklearn.cross_validation import train_test_split

from sklearn.model_selection import  train_test_split

#x为数据集的feature熟悉，y为label.

X_train, X_valid, y_train, y_valid = train_test_split(X_train, y_train, test_size = 0.2)

# 根据不同的backend定下不同的格式

if K.image_dim_ordering() == 'th':

    X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)

    X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)

    X_valid = X_valid.reshape(X_valid.shape[0], 1, img_rows, img_cols)

    input_shape = (1, img_rows, img_cols)

else:

    X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)

    X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)

    X_valid = X_valid.reshape(X_valid.shape[0], img_rows, img_cols,1)

    input_shape = (img_rows, img_cols, 1)

# 类型转换

X_train = X_train.astype('float32')

X_test = X_test.astype('float32')

X_valid = X_valid.astype('float32')

X_train /= 255

X_test /= 255

X_valid /= 255

print('X_train shape:', X_train.shape)

print(X_train.shape[0], 'train samples')

print(X_test.shape[0], 'test samples')

print(X_valid.shape[0], 'valid samples')

# 转换为one_hot类型

Y_train = np_utils.to_categorical(y_train, nb_classes)

Y_test = np_utils.to_categorical(y_test, nb_classes)

Y_valid = np_utils.to_categorical(y_valid, nb_classes)

#构建模型

model = Sequential()

model.add(Convolution2D(nb_filters, (kernel_size[0], kernel_size[1]),

                        padding='same',

                        input_shape=input_shape)) # 卷积层1

model.add(Activation('relu')) #激活层

model.add(Convolution2D(nb_filters, (kernel_size[0], kernel_size[1]))) #卷积层2

model.add(Activation('relu')) #激活层

model.add(MaxPooling2D(pool_size=pool_size)) #池化层

model.add(Dropout(0.25)) #神经元随机失活

model.add(Flatten()) #拉成一维数据

model.add(Dense(128)) #全连接层1

model.add(Activation('relu')) #激活层

model.add(Dropout(0.5)) #随机失活

model.add(Dense(nb_classes)) #全连接层2

model.add(Activation('softmax')) #Softmax评分

#编译模型

model.compile(loss='categorical_crossentropy',

              optimizer='adadelta',

              metrics=['accuracy'])

#训练模型

model.fit(X_train, Y_train, batch_size=batch_size, epochs=epochs,

          verbose=1, validation_data=(X_valid, Y_valid))

#评估模型

score = model.evaluate(X_test, Y_test, verbose=0)

print('Test score:', score[0])

print('Test accuracy:', score[1])