CNN的TensorFlow实现
在本节中，我们将了解 CNN 的 TensorFlow 实现。需要整个网络的执行和适当维度的步骤如下所示 -
步骤 1 − 包括计算 CNN 模型所需的 TensorFlow 和数据集模块所需的模块。
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
步骤 2 - 声明一个函数调用 run_cnn()，其中包括各种参数和优化变量以及数据占位符的声明。这些优化变量将声明训练模式。
def run_cnn():
mnist = input_data.read_data_sets("MNIST_data/", one_hot = True)
learning_rate = 0.0001
epochs = 10
batch_size = 50
步骤 3 - 在这一步中，我们将使用输入参数声明训练数据占位符 - 28 x 28 像素 = 784。这是从 mnist.train.nextbatch().
我们可以根据我们的要求重塑张量。第一个值 (-1) 告诉函数根据传递给它的数据量动态调整该维度。中间的两个尺寸设置为图像大小（即 28 x 28）。
x = tf.placeholder(tf.float32, [None, 784])
x_shaped = tf.reshape(x, [-1, 28, 28, 1])
y = tf.placeholder(tf.float32, [None, 10])
步骤 4 - 现在创建一些卷积层很重要 -
layer1 = create_new_conv_layer(x_shaped, 1, 32, [5, 5], [2, 2], name = 'layer1')
layer2 = create_new_conv_layer(layer1, 32, 64, [5, 5], [2, 2], name = 'layer2')
步骤 5- 让我们为完全连接的输出阶段准备好输出 - 经过两层步长 2 池化，尺寸为 28 x 28，尺寸为 14 x 14 或最小 7 x 7 x,y 坐标，但具有 64输出通道。要创建完全连接的“密集”层，新形状需要为 [-1, 7 x 7 x 64]。我们可以为这一层设置一些权重和偏置值，然后用 ReLU 激活。
flattened = tf.reshape(layer2, [-1, 7 * 7 * 64])
wd1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1000], stddev = 0.03), name = 'wd1')
bd1 = tf.Variable(tf.truncated_normal([1000], stddev = 0.01), name = 'bd1')
dense_layer1 = tf.matmul(flattened, wd1) + bd1
dense_layer1 = tf.nn.relu(dense_layer1)
步骤 6 - 具有特定 softmax 激活和所需优化器的另一层定义了准确性评估，这使得初始化算子的设置。
wd2 = tf.Variable(tf.truncated_normal([1000, 10], stddev = 0.03), name = 'wd2')
bd2 = tf.Variable(tf.truncated_normal([10], stddev = 0.01), name = 'bd2')
dense_layer2 = tf.matmul(dense_layer1, wd2) + bd2
y_ = tf.nn.softmax(dense_layer2)
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits = dense_layer2, labels = y))
optimiser = tf.train.AdamOptimizer(learning_rate = learning_rate).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init_op = tf.global_variables_initializer()
步骤 7- 我们应该设置记录变量。这会添加一个摘要来存储数据的准确性。
tf.summary.scalar('accuracy', accuracy)
merged = tf.summary.merge_all()
writer = tf.summary.FileWriter('E:\TensorFlowProject')
with tf.Session() as sess:
sess.run(init_op)
total_batch = int(len(mnist.train.labels) / batch_size)
for epoch in range(epochs):
avg_cost = 0
for i in range(total_batch):
batch_x, batch_y = mnist.train.next_batch(batch_size = batch_size)
_, c = sess.run([optimiser, cross_entropy], feed_dict = {
x:batch_x, y: batch_y})
avg_cost += c / total_batch
test_acc = sess.run(accuracy, feed_dict = {x: mnist.test.images, y:
mnist.test.labels})
summary = sess.run(merged, feed_dict = {x: mnist.test.images, y:
mnist.test.labels})
writer.add_summary(summary, epoch)
print("\nTraining complete!")
writer.add_graph(sess.graph)
print(sess.run(accuracy, feed_dict = {x: mnist.test.images, y:
mnist.test.labels}))
def create_new_conv_layer(
input_data, num_input_channels, num_filters,filter_shape, pool_shape, name):
conv_filt_shape = [
filter_shape[0], filter_shape[1], num_input_channels, num_filters]
weights = tf.Variable(
tf.truncated_normal(conv_filt_shape, stddev = 0.03), name = name+'_W')
bias = tf.Variable(tf.truncated_normal([num_filters]), name = name+'_b')
#Out layer defines the output
out_layer =
tf.nn.conv2d(input_data, weights, [1, 1, 1, 1], padding = 'SAME')
out_layer += bias
out_layer = tf.nn.relu(out_layer)
ksize = [1, pool_shape[0], pool_shape[1], 1]
strides = [1, 2, 2, 1]
out_layer = tf.nn.max_pool(
out_layer, ksize = ksize, strides = strides, padding = 'SAME')
return out_layer
if __name__ == "__main__":
run_cnn()
以下是上述代码生成的输出 -
See @{tf.nn.softmax_cross_entropy_with_logits_v2}.
2018-09-19 17:22:58.802268: I
T:\src\github\tensorflow\tensorflow\core\platform\cpu_feature_guard.cc:140]
Your CPU supports instructions that this TensorFlow binary was not compiled to
use: AVX2
2018-09-19 17:25:41.522845: W
T:\src\github\tensorflow\tensorflow\core\framework\allocator.cc:101] Allocation
of 1003520000 exceeds 10% of system memory.
2018-09-19 17:25:44.630941: W
T:\src\github\tensorflow\tensorflow\core\framework\allocator.cc:101] Allocation
of 501760000 exceeds 10% of system memory.
Epoch: 1 cost = 0.676 test accuracy: 0.940
2018-09-19 17:26:51.987554: W
T:\src\github\tensorflow\tensorflow\core\framework\allocator.cc:101] Allocation
of 1003520000 exceeds 10% of system memory.
如果我们观察上述表示，每个连接都会学习隐藏神经元的权重，并与从一层到另一层的移动相关联。在这里，单个神经元不时地执行转换。这个过程称为“卷积”。从输入层到隐藏特征图的连接映射被定义为“共享权重”，包含的偏差称为“共享偏差”。CNN 或卷积神经网络使用池化层，这些层位于 CNN 声明之后。它将用户的输入作为来自卷积网络的特征图，并准备一个浓缩的特征图。池化层有助于使用前一层的神经元创建层。