keras下解決 example 案例中 MNIST 數(shù)據(jù)集下載不了的問題

keras 源碼中下載MNIST的方式是 path = get_file(path, origin='https://s3.amazonaws.com/img-datasets/mnist.npz')，數(shù)據(jù)源是通過 url = https://s3.amazonaws.com/img-datasets/mnist.npz 進(jìn)行下載的。訪問該 url 地址被墻了，導(dǎo)致 MNIST 相關(guān)的案例都卡在數(shù)據(jù)下載的環(huán)節(jié)。本文主要提供解決方案，讓需要的讀者可以跑案例的代碼感受一下。

下載 mnist.npz 數(shù)據(jù)集

本文使用的 mnist.npz 數(shù)據(jù)集是通過一個(gè) japan 的服務(wù)器下載得到的，在此免費(fèi)分享給大家。如果下載有問題的話，可以留言哈。

下載鏈接：https://pan.baidu.com/s/1jH6uFFC密碼: dw3d

下載后文件放在*.py所在目錄下

改造原來(lái)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()

運(yùn)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

完整代碼如下：

# -*- 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

# 全局變量

batch_size = 128

nb_classes = 10

epochs = 5

# input image dimensions

img_rows, img_cols = 28, 28

# 卷積濾波器的數(shù)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為數(shù)據(jù)集的feature熟悉，y為label.

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

# 根據(jù)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)

# 類型轉(zhuǎn)換

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')

# 轉(zhuǎn)換為one_hot類型

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)

#構(gòu)建模型

model = Sequential()

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

? ? ? ? ? ? ? ? ? ? ? ? padding='same',

? ? ? ? ? ? ? ? ? ? ? ? input_shape=input_shape)) # 卷積層1

model.add(Activation('relu')) #激活層

model.add(Convolution2D(nb_filters, (kernel_size[0], kernel_size[1]))) #卷積層2

model.add(Activation('relu')) #激活層

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

model.add(Dropout(0.25)) #神經(jīng)元隨機(jī)失活

model.add(Flatten()) #拉成一維數(shù)據(jù)

model.add(Dense(128)) #全連接層1

model.add(Activation('relu')) #激活層

model.add(Dropout(0.5)) #隨機(jī)失活

model.add(Dense(nb_classes)) #全連接層2

model.add(Activation('softmax')) #Softmax評(píng)分

#編譯模型

model.compile(loss='categorical_crossentropy',

? ? ? ? ? ? ? optimizer='adadelta',

? ? ? ? ? ? ? metrics=['accuracy'])

#訓(xùn)練模型

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

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

#評(píng)估模型

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

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

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

最后編輯于 ：
?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請(qǐng)聯(lián)系作者
【社區(qū)內(nèi)容提示】社區(qū)部分內(nèi)容疑似由AI輔助生成，瀏覽時(shí)請(qǐng)結(jié)合常識(shí)與多方信息審慎甄別。
平臺(tái)聲明：文章內(nèi)容（如有圖片或視頻亦包括在內(nèi)）由作者上傳并發(fā)布，文章內(nèi)容僅代表作者本人觀點(diǎn)，簡(jiǎn)書系信息發(fā)布平臺(tái)，僅提供信息存儲(chǔ)服務(wù)。

友情鏈接更多精彩內(nèi)容