# -*- coding: utf-8 -*-
import tensorflow as tf
def inference(image,batch_size,n_classes):
#conv1 image -[batch_size,image_w,image_h,channels] 类型 :tensor image_w,h 以256*256为例
with tf.variable_scope('conv1') as scope:
#3*3*3 卷积核 ,16 个神经元
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(image,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)
#print("image的shape是",image.get_shape())
#print("conv1的shape是",conv1.get_shape())
#pooling and norm1
with tf.variable_scope('pool1_norm1') 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')
#conv2
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 = scope.name)
print("conv2的shape是",conv2.get_shape())
#norm2 and pooling2
with tf.variable_scope('pool2_norm2') 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 = [1,2,2,1],padding = 'SAME',name = 'pooling2')
print("pool2的shape是",pool2.get_shape())
#local1
with tf.variable_scope('local1') as scope:
dim = 1
for d in pool2.get_shape()[1:].as_list():
dim *= d #如果是pool2维度信息-[batch_size,64,64,16] 那么dim就是65536 = 64*64*16
reshape = tf.reshape(pool2, [batch_size, -1]) #将pool2拉直-[8,65536] batch_size=8
#tf.get_shape() 中的元素只能是tensor,且返回的是一个元组但是可用
#x.get_shape().as_list() 变成list。
#tf.shape()中的元素可以是tensor,list,array
# reshape = tf.reshape(pool2,[batch_size,65536])
# print(reshape.get_shape().as_list())
# dim = reshape.get_shape().as_list()
# print(dim[1])
weights = tf.get_variable('weights',shape = [dim,128],
dtype = tf.float32,
initializer = tf.truncated_normal_initializer(stddev = 0.1,dtype = tf.float32))
biases = tf.get_variable('biases',shape = [128],dtype = tf.float32,initializer = tf.constant_initializer(0.1))
local1 = tf.nn.relu(tf.matmul(reshape,weights)+biases,name = scope.name)
#local2
with tf.variable_scope('local2') 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))
local2 = tf.nn.relu(tf.matmul(local1,weights)+biases,name = scope.name)
#softmax
with tf.variable_scope('softmax_linear') as scope:
weights = tf.get_variable('weights',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(local2,weights),biases,name = 'softmax')
#最后这里不用加激活函数,因为计算调用计算loss的函数的时候,其会在内部实现。所以这里不用手动写了
return softmax_linear
def losses(logits,labels):
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") # batch中每一个图像都有一个cross_entropy
loss = tf.reduce_mean(cross_entropy,name= 'loss') #全部加和求平均
return loss
def trainning(loss,learning_rate):
with tf.variable_scope('trainning') as scope:
optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate)
global_step = tf.Variable(0,name = 'global_step',trainable = False) #global_step 计数的作用,计算运行了多少个batch
train_op = optimizer.minimize(loss,global_step = global_step)
return train_op
def evaluation(logits,label):
with tf.variable_scope('evaluation') as scope:
correct = tf.nn.in_top_k(logits,label,1) #correct里面的类型是bool类型[true,false,..]
correct = tf.cast(correct,tf.float16)#[1,0,...]
accuary = tf.reduce_mean(correct)
tf.summary.scalar(scope.name + '/accuary',accuary)
return accuary
cats and dogs tensorflow - 1模型建立
最新推荐文章于 2024-08-19 21:12:55 发布