写在前面
本文介绍了使用TensorFlow在MNIST数据集上构建基础的卷积神经网络来实现识别手写字符的任务,包括:{两层的卷基层}+{一层relu的全链接层}+{一层softmax的全链接层}。由于结构简单,代码清晰,文章整体就以代码走向为主,阅读省力省事。
1. Load MNIST Data
# load MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
2. Start TensorFlow InterativeSession
# start TensorFlow InterativeSession
import tensorflow as tf
sess = tf.InteractiveSession()
3. Placeholders
# Placeholders
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
4. Weight Initialization Function Define
# Weight Initialization
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
5. Convolution and Pooling Function Define
# Convolution and Pooling
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
6. First Convolutional Layer
# First Convolutional Layer
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
# (The convolutional will compute 32 features for each 5x5 patch)
# ([5, 5, 1, 32], "5, 5": patch_size, 1: number of input channels, 32: number of output channels)
x_image = tf.reshape(x, [-1, 28, 28, 1])
# (reshape x to a 4d tensor)
# (2nd & 3rd dimensions: image width and height. The final dimension: the number of color channels)
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
7. Sencond Convolution Layer
# Sencond Convolution Layer
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
8. Fully Connected Layer
# Fully Connected Layer
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
9. Dropout
# Dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
10. Readout Layer
# Readout Layer
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
11. Train and Evaluate the Model
# Train and Evaluate the Model
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print("test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
12. The Output
/usr/bin/python2.7 /home/zhao/PycharmProjects/TensorFlow/tutorial/Convolutional.py
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcurand.so locally
Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
I tensorflow/core/common_runtime/gpu/gpu_init.cc:102] Found device 0 with properties:
name: GeForce GTX 970
major: 5 minor: 2 memoryClockRate (GHz) 1.266
pciBusID 0000:01:00.0
Total memory: 4.00GiB
Free memory: 3.59GiB
I tensorflow/core/common_runtime/gpu/gpu_init.cc:126] DMA: 0
I tensorflow/core/common_runtime/gpu/gpu_init.cc:136] 0: Y
I tensorflow/core/common_runtime/gpu/gpu_device.cc:838] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 970, pci bus id: 0000:01:00.0)
step 0, training accuracy 0.12
step 100, training accuracy 0.84
step 200, training accuracy 0.92
step 300, training accuracy 0.86
step 400, training accuracy 0.98
...
step 19700, training accuracy 1
step 19800, training accuracy 1
step 19900, training accuracy 0.98
W tensorflow/core/common_runtime/bfc_allocator.cc:213] Ran out of memory trying to allocate 2.59GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
W tensorflow/core/common_runtime/bfc_allocator.cc:213] Ran out of memory trying to allocate 1.34GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
W tensorflow/core/common_runtime/bfc_allocator.cc:213] Ran out of memory trying to allocate 3.90GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
test accuracy 0.9926
测试精度达到0.9926,还是不错的。