【问题标题】:What do i have to modify to load the SVHN Dataset in my code?我必须修改什么才能在我的代码中加载 SVHN 数据集?
【发布时间】:2019-09-27 06:08:22
【问题描述】:

我使用 Keras MNIST 数据集,现在我想使用谷歌数据集街景门牌号 (SVHN) 来训练我的程序。我不知道我必须修改什么才能在我的代码中加载 SVHN 数据集(文件 .mat)

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras import backend as K
import tensorflow as tf
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense, Conv2D, Dropout, Flatten, MaxPooling2D


img_rows, img_cols = 28, 28

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

image_index = 7777 
print(y_train[image_index])
plt.imshow(x_train[image_index], cmap='Greys')

x_train.shape

x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
input_shape = (28, 28, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')

x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print('Number of images in x_train', x_train.shape[0])
print('Number of images in x_test', x_test.shape[0])


model = Sequential()
model.add(Conv2D(28, kernel_size=(3,3), input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(128, activation=tf.nn.relu))
model.add(Dropout(0.2))
model.add(Dense(10,activation=tf.nn.softmax))

model.compile(optimizer='adam', 
          loss='sparse_categorical_crossentropy', 
          metrics=['accuracy'])
model.fit(x=x_train,y=y_train, epochs=2)

model.evaluate(x_test, y_test)


image_index = 9999
plt.imshow(x_test[image_index].reshape(28, 28),cmap='Greys')
pred = model.predict(x_test[image_index].reshape(1, img_rows, img_cols, 1))
print(pred.argmax())

【问题讨论】:

    标签: python tensorflow keras deep-learning


    【解决方案1】:

    您可以使用scipy.io.loadmat 读取.mat 文件,它返回一个字典,其值为numpy 数组。请参阅文档here。您可能需要根据您的要求重塑数据。

    注意他们提到了

    您需要一个 HDF5 python 库来读取 MATLAB 7.3 格式的 mat 文件。

    【讨论】:

      猜你喜欢
      • 2011-04-21
      • 2015-03-16
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 2021-01-29
      • 1970-01-01
      • 2012-01-05
      相关资源
      最近更新 更多