import tensorflow as tf
import tensorflow as tf
from tensorflow. keras import datasets, layers, models
import matplotlib. pyplot as plt
( train_images, train_labels) , \
( test_images, test_labels) = datasets. mnist. load_data( )
train_images, test_images = train_images/ 255.0 , test_images/ 255.0
train_images. shape, test_images. shape, train_labels. shape, test_labels. shape
((60000, 28, 28), (10000, 28, 28), (60000,), (10000,))
plt. figure( figsize= ( 10 , 10 ) )
for i in range ( 20 ) :
plt. subplot( 5 , 10 , i+ 1 )
plt. xticks( [ ] )
plt. yticks( [ ] )
plt. grid( False )
plt. imshow( train_images[ i] , cmap= plt. cm. binary)
plt. xlabel( train_labels[ i] )
plt. show( )
train_images = train_images. reshape( ( 60000 , 28 , 28 , 1 ) )
test_images = test_images. reshape( ( 10000 , 28 , 28 , 1 ) )
train_images. shape, test_images. shape, train_labels. shape, test_labels. shape
((60000, 28, 28, 1), (10000, 28, 28, 1), (60000,), (10000,))
model = models. Sequential( [
layers. Conv2D( 32 , ( 3 , 3 ) , activation= 'relu' , input_shape= ( 28 , 28 , 1 ) ) ,
layers. MaxPooling2D( ( 2 , 2 ) ) ,
layers. Conv2D( 64 , ( 3 , 3 ) , activation= 'relu' ) ,
layers. MaxPool2D( ( 2 , 2 ) ) ,
layers. Flatten( ) ,
layers. Dense( 64 , activation= 'relu' ) ,
layers. Dense( 10 )
] )
model. summary( )
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 26, 26, 32) 320
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 13, 13, 32) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 11, 11, 64) 18496
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 5, 5, 64) 0
_________________________________________________________________
flatten (Flatten) (None, 1600) 0
_________________________________________________________________
dense (Dense) (None, 64) 102464
_________________________________________________________________
dense_1 (Dense) (None, 10) 650
=================================================================
Total params: 121,930
Trainable params: 121,930
Non-trainable params: 0
_________________________________________________________________
2022-01-07 23:45:52.268745: I tensorflow/core/platform/cpu_feature_guard.cc:145] This TensorFlow binary is optimized with Intel(R) MKL-DNN to use the following CPU instructions in performance critical operations: SSE4.1 SSE4.2
To enable them in non-MKL-DNN operations, rebuild TensorFlow with the appropriate compiler flags.
2022-01-07 23:45:52.275905: I tensorflow/core/common_runtime/process_util.cc:115] Creating new thread pool with default inter op setting: 8. Tune using inter_op_parallelism_threads for best performance.
model. compile ( optimizer= 'adam' ,
loss= tf. keras. losses. SparseCategoricalCrossentropy( from_logits= True ) ,
metrics= [ 'accuracy' ]
)
history = model. fit( train_images,
train_labels,
epochs= 10 ,
validation_data= ( test_images, test_labels)
)
Train on 60000 samples, validate on 10000 samples
Epoch 1/10
60000/60000 [==============================] - 138s 2ms/sample - loss: 0.1428 - accuracy: 0.9568 - val_loss: 0.0579 - val_accuracy: 0.9809
Epoch 2/10
60000/60000 [==============================] - 134s 2ms/sample - loss: 0.0456 - accuracy: 0.9861 - val_loss: 0.0388 - val_accuracy: 0.9877
Epoch 3/10
60000/60000 [==============================] - 132s 2ms/sample - loss: 0.0328 - accuracy: 0.9897 - val_loss: 0.0304 - val_accuracy: 0.9902
Epoch 4/10
60000/60000 [==============================] - 131s 2ms/sample - loss: 0.0232 - accuracy: 0.9922 - val_loss: 0.0301 - val_accuracy: 0.9897
Epoch 5/10
60000/60000 [==============================] - 134s 2ms/sample - loss: 0.0176 - accuracy: 0.9943 - val_loss: 0.0325 - val_accuracy: 0.9894
Epoch 6/10
60000/60000 [==============================] - 134s 2ms/sample - loss: 0.0135 - accuracy: 0.9956 - val_loss: 0.0307 - val_accuracy: 0.9907
Epoch 7/10
60000/60000 [==============================] - 134s 2ms/sample - loss: 0.0119 - accuracy: 0.9961 - val_loss: 0.0319 - val_accuracy: 0.9905
Epoch 8/10
60000/60000 [==============================] - 134s 2ms/sample - loss: 0.0086 - accuracy: 0.9973 - val_loss: 0.0327 - val_accuracy: 0.9905
Epoch 9/10
60000/60000 [==============================] - 132s 2ms/sample - loss: 0.0080 - accuracy: 0.9974 - val_loss: 0.0296 - val_accuracy: 0.9918
Epoch 10/10
60000/60000 [==============================] - 130s 2ms/sample - loss: 0.0065 - accuracy: 0.9979 - val_loss: 0.0314 - val_accuracy: 0.9911
plt. imshow( test_images[ 1 ] )
<matplotlib.image.AxesImage at 0x7fd441a74550>
pre = model. predict( test_images)
pre[ 1 ]
array([-7.576601 , 0.24191436, 22.48119 , -7.913903 , -6.1873503 ,
-9.024768 , -0.274709 , -1.0671589 , 3.3178928 , -9.065157 ],
dtype=float32)
网络结构
各层的作用
输入层:用于将数据输入到训练网络 卷积层:使用卷积核提取图片特征 池化层:进行下采样,用更高层的抽象表示图像特征 Flatten层:将多维的输入一维化,常用在卷积层到全连接层的过渡 全连接层:起到“特征提取器”的作用 输出层:输出结果