快乐学习
前程无忧、中华英才非你莫属!

TensorFlow——训练自己的数据(二)模型设计

参考:Tensorflow教程-猫狗大战数据集
文件:model.py
网络结构定义 
一个简单的卷积神经网络,卷积+池化层x2,全连接层x2,最后一个softmax层做分类。 
函数:def inference(images, batch_size, n_classes):

输入参数: 
images,image batch、4D tensor、tf.float32、[batch_size, width, height, channels]

返回参数: 
logits, float、 [batch_size, n_classes]

卷积层1 
16个3×3的卷积核(3通道),padding=’SAME’,表示padding后卷积的图与原图尺寸一致,激活函数relu()

with tf.variable_scope(‘conv1’) as scope:
weights = tf.get_variable(‘weights’,
shape = [3,3,3, 16],
dtype = tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1,dtype=tf.float32))
biases = tf.get_variable(‘biases’,
shape=[16],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
conv = tf.nn.conv2d(images, weights, strides=[1,1,1,1], padding=‘SAME’)
pre_activation = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(pre_activation, name= scope.name)

池化层1 
3×3最大池化,步长strides为2,池化后执行lrn()操作,局部响应归一化,对训练有利。

with tf.variable_scope(‘pooling1_lrn’) as scope:
pool1 = tf.nn.max_pool(conv1, ksize=[1,3,3,1],strides=[1,2,2,1],padding=‘SAME’, name=‘pooling1’)
norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001/9.0,beta=0.75,name=‘norm1’)

卷积层2 
16个3×3的卷积核(16通道),padding=’SAME’,表示padding后卷积的图与原图尺寸一致,激活函数relu()

with tf.variable_scope(‘conv2’) as scope:
weights = tf.get_variable(‘weights’,
shape=[3,3,16,16],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.1,dtype=tf.float32))
biases = tf.get_variable(‘biases’,
shape=[16],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
conv = tf.nn.conv2d(norm1, weights, strides=[1,1,1,1],padding=‘SAME’)
pre_activation = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(pre_activation, name=‘conv2’)

池化层2 
3×3最大池化,步长strides为2,池化后执行lrn()操作,

#pool2 and norm2with tf.variable_scope(‘pooling2_lrn’) as scope:
norm2 = tf.nn.lrn(conv2, depth_radius=4, bias=1.0, alpha=0.001/9.0,beta=0.75,name=‘norm2’)
pool2 = tf.nn.max_pool(norm2, ksize=[1,3,3,1], strides=[1,1,1,1],padding=‘SAME’,name=‘pooling2’)

全连接层3 
128个神经元,将之前pool层的输出reshape成一行,激活函数relu()

with tf.variable_scope(‘local3’) as scope:
reshape = tf.reshape(pool2, shape=[batch_size, –1])
dim = reshape.get_shape()[1].value
weights = tf.get_variable(‘weights’,
shape=[dim,128],
dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.005,dtype=tf.float32))
biases = tf.get_variable(‘biases’,
shape=[128],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)

全连接层4 
128个神经元,激活函数relu()

#local4
with tf.variable_scope(‘local4’) as scope:
weights = tf.get_variable(‘weights’,
shape=[128,128],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.005,dtype=tf.float32))
biases = tf.get_variable(‘biases’,
shape=[128],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name=‘local4’)

Softmax回归层 
将前面的FC层输出,做一个线性回归,计算出每一类的得分,在这里是2类,所以这个层输出的是两个得分。

# softmaxwith tf.variable_scope(‘softmax_linear’) as scope:
weights = tf.get_variable(‘softmax_linear’,
shape=[128, n_classes],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.005,dtype=tf.float32))
biases = tf.get_variable(‘biases’,
shape=[n_classes],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
softmax_linear = tf.add(tf.matmul(local4, weights), biases, name=‘softmax_linear’)
return softmax_linear

loss计算 
将网络计算得出的每类得分与真实值进行比较,得出一个loss损失值,这个值代表了计算值与期望值的差距。这里使用的loss函数是交叉熵。一批loss取平均数。最后调用了summary.scalar()记录下这个标量数据,在TensorBoard中进行可视化。 
函数:def losses(logits, labels):

传入参数:logits,网络计算输出值。labels,真实值,在这里是0或者1
返回参数:loss,损失值
with tf.variable_scope(‘loss’) as scope:
cross_entropy =tf.nn.sparse_softmax_cross_entropy_with_logits
(logits=logits, labels=labels, name=‘xentropy_per_example’)
loss = tf.reduce_mean(cross_entropy, name=‘loss’)
tf.summary.scalar(scope.name+‘/loss’, loss)
return loss

loss损失值优化 
目的就是让loss越小越好,使用的是AdamOptimizer优化器 
函数:def trainning(loss, learning_rate):

输入参数:loss。learning_rate,学习速率。
返回参数:train_op,训练op,这个参数要输入sess.run中让模型去训练。
with tf.name_scope(‘optimizer’):
optimizer = tf.train.AdamOptimizer(learning_rate= learning_rate)
global_step = tf.Variable(0, name=‘global_step’, trainable=False)
train_op = optimizer.minimize(loss, global_step= global_step)
return train_op

评价/准确率计算 
计算出平均准确率来评价这个模型,在训练过程中按批次计算(每隔N步计算一次),可以看到准确率的变换情况。 
函数:def evaluation(logits, labels):

输入参数:logits,网络计算值。labels,标签,也就是真实值,在这里是0或者1。
返回参数:accuracy,当前step的平均准确率,也就是在这些batch中多少张图片被正确分类了。
with tf.variable_scope(‘accuracy’) as scope:
correct = tf.nn.in_top_k(logits, labels, 1)
correct = tf.cast(correct, tf.float16)
accuracy = tf.reduce_mean(correct)
tf.summary.scalar(scope.name+‘/accuracy’, accuracy)
return accuracy

作者:xinyu3307


打赏

未经允许不得转载:同乐学堂 » TensorFlow——训练自己的数据(二)模型设计

分享到:更多 ()

评论 抢沙发

  • 昵称 (必填)
  • 邮箱 (必填)
  • 网址

特别的技术,给特别的你!

联系QQ:1071235258QQ群:226134712
error: Sorry,暂时内容不可复制!