用 Keras 在 MNIST 上实现卷积神经网络

最新推荐文章于 2024-02-28 15:21:44 发布

原创最新推荐文章于 2024-02-28 15:21:44 发布 · 985 阅读

3 ·

CC 4.0 BY-SA版权

文章标签：

#keras #python #深度学习

Keras 专栏收录该内容

2 篇文章

订阅专栏

本文介绍了一个使用Keras库实现的简单卷积神经网络（CNN），该网络在MNIST数据集上进行训练，达到了99.25%的测试准确率。网络结构包括两个卷积层、最大池化层、丢弃层和平坦化层等。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

官方教程：keras/examples/mnist_cnn.py

'''Trains a simple convnet on the MNIST dataset.
Gets to 99.25% test accuracy after 12 epochs
(there is still a lot of margin for parameter tuning).
16 seconds per epoch on a GRID K520 GPU.
'''

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

batch_size = 128
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    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)
    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)
    input_shape = (img_rows, img_cols, 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(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.summary()

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

运行结果：

Using TensorFlow backend.
x_train shape: (60000, 28, 28, 1)
60000 train samples
10000 test samples
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 26, 26, 32)        320       
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 24, 24, 64)        18496     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 12, 12, 64)        0         
_________________________________________________________________
dropout_1 (Dropout)          (None, 12, 12, 64)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 9216)              0         
_________________________________________________________________
dense_1 (Dense)              (None, 128)               1179776   
_________________________________________________________________
dropout_2 (Dropout)          (None, 128)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 10)                1290      
=================================================================
Total params: 1,199,882
Trainable params: 1,199,882
Non-trainable params: 0
_________________________________________________________________
Train on 60000 samples, validate on 10000 samples
Epoch 1/12
2019-04-02 13:51:57.914231: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:1392] Found device 0 with properties: 
name: GeForce MX150 major: 6 minor: 1 memoryClockRate(GHz): 1.0375
pciBusID: 0000:01:00.0
totalMemory: 2.00GiB freeMemory: 1.62GiB
2019-04-02 13:51:57.914777: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:1471] Adding visible gpu devices: 0
2019-04-02 13:51:58.752681: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:952] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-04-02 13:51:58.753133: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:958]      0 
2019-04-02 13:51:58.753369: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:971] 0:   N 
2019-04-02 13:51:58.753723: I c:\users\user\source\repos\tensorflow\tensorflow\core\common_runtime\gpu\gpu_device.cc:1084] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1386 MB memory) -> physical GPU (device: 0, name: GeForce MX150, pci bus id: 0000:01:00.0, compute capability: 6.1)

  128/60000 [..............................] - ETA: 47:50 - loss: 2.3157 - acc: 0.0547
  384/60000 [..............................] - ETA: 16:07 - loss: 2.2406 - acc: 0.2240
...
59648/60000 [============================>.] - ETA: 0s - loss: 0.2782 - acc: 0.9143
59904/60000 [============================>.] - ETA: 0s - loss: 0.2774 - acc: 0.9145
60000/60000 [==============================] - 27s 447us/step - loss: 0.2771 - acc: 0.9146 - val_loss: 0.0672 - val_acc: 0.9787
Epoch 2/12

  128/60000 [..............................] - ETA: 20s - loss: 0.1301 - acc: 0.9766
  384/60000 [..............................] - ETA: 19s - loss: 0.1233 - acc: 0.9609
...
  896/60000 [..............................] - ETA: 19s - loss: 0.1142 - acc: 0.9654
 1152/60000 [..............................] - ETA: 19s - loss: 0.1018 - acc: 0.9696
Epoch 12/12

  128/60000 [..............................] - ETA: 21s - loss: 0.0644 - acc: 0.9766
  384/60000 [..............................] - ETA: 20s - loss: 0.0334 - acc: 0.9870
...
59520/60000 [============================>.] - ETA: 0s - loss: 0.0271 - acc: 0.9917
59776/60000 [============================>.] - ETA: 0s - loss: 0.0273 - acc: 0.9917
60000/60000 [==============================] - 23s 377us/step - loss: 0.0273 - acc: 0.9917 - val_loss: 0.0293 - val_acc: 0.9904
Test loss: 0.02927316072658082
Test accuracy: 0.9904