tensorflow系列之_pspnet网络

目标检测领域的实例分割网络 PSPnet,基于像素级的分类，提出了一种金字塔池化模块，金字塔层级的数量和每一层的大小都可以进行调整

主题结构是一个提去特征的基础网络（resnet/mobilenet）+金字塔池化。

项目中为了减小网络参数大小和部署方便，backbone采用的mobilenetv1。

mobilenet_v1.py代码(mobilenet_v1输出 f1,f2,f3,f4,f5不同尺度的特征)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @time: 2020/6/22 19:27"""
标准的mobilenet_v1
只能接受输入224*224大小的图片
输出 f1,f2,f3,f4,f5不同尺度的特征图"""import tensorflow as tf
import tensorflow.contrib.slim as slimdef mobilenet(inputs,num_classes=100,is_training=True,width_multiplier=1,scope='mobilenet'):""":param inputs: [batch_size,h,w,c]:param num_classes::param is_training::param width_multiplier::param scope::return: logits: the pre_softmax activationsend_points: 包含了特征图的dict"""def _depthwise_separable_conv(inputs,num_pwc_filters,width_multiplier,sc,downsample=False):"""depth-wise separable 卷积层:param inputs::param num_pwc_filters: 点卷积和的个数:param width_multiplier::param sc:命名空间:param dowmnsample::return:"""num_pwc_filters = round(num_pwc_filters * width_multiplier)_stride = 2 if downsample else 1 # 如果下采样就为2，否则为1# skip pointwise by setting num_outputs=None ，# pointwise 卷积的卷积核个数，如果为空，将跳过pointwise卷积的步骤.# 深度可分离卷积depthwise_conv = slim.separable_convolution2d(inputs,num_outputs=None,stride=_stride,depth_multiplier=1,kernel_size=[3, 3],scope=sc + '/depthwise_conv')bn = slim.batch_norm(depthwise_conv, scope=sc + '/dw_batch_norm')#点卷积 就是1*1的普通卷积pointwise_conv = slim.conv2d(bn,num_pwc_filters,kernel_size=[1, 1],scope=sc + '/pointwise_conv')bn = slim.batch_norm(pointwise_conv, scope=sc + '/pw_batch_norm')return bnwith tf.variable_scope(scope) as sc:end_points_collection=sc.name+'_end_points'with slim.arg_scope([slim.conv2d,slim.separable_convolution2d],activation_fn=None,outputs_collections=[end_points_collection]):with slim.arg_scope([slim.batch_norm],is_training=is_training,activation_fn=tf.nn.relu,fused=True):net=slim.conv2d(inputs,round(32*width_multiplier),[3,3],stride=2,padding='SAME',scope='conv_1') # [batch_size,h/2,w/2,32]net=slim.batch_norm(net,scope='conv_1/batch_norm')net=_depthwise_separable_conv(net,64,width_multiplier,sc='conv_ds_2') # [batch_size,h/2,w/2,64]net=_depthwise_separable_conv(net,128,width_multiplier,downsample=True,sc='conv_ds_3')# 下采样 [batch_size,h/4,w/4,128]net=_depthwise_separable_conv(net,128,width_multiplier,sc='conv_ds_4') #[batch_size,h/4,w/4,128]net = _depthwise_separable_conv(net, 256, width_multiplier, downsample=True, sc='conv_ds_5')  # 下采样 [batch_size,h/8,w/8,256]net=_depthwise_separable_conv(net,256,width_multiplier,sc='conv_ds_6') #[batch_size,h/8,w/8,256]net = _depthwise_separable_conv(net, 512, width_multiplier, downsample=True, sc='conv_ds_7')  # 下采样 # [batch_size,h/16,w/16,256]net = _depthwise_separable_conv(net, 512, width_multiplier, sc='conv_ds_8') # [batch_size,h/16,w/16,512]net = _depthwise_separable_conv(net, 512, width_multiplier, sc='conv_ds_9') # [batch_size,h/16,w/16,512]net = _depthwise_separable_conv(net, 512, width_multiplier, sc='conv_ds_10') # [batch_size,h/16,w/16,512]net = _depthwise_separable_conv(net, 512, width_multiplier, sc='conv_ds_11')# [batch_size,h/16,w/16,512]net = _depthwise_separable_conv(net, 512, width_multiplier, sc='conv_ds_12')# [batch_size,h/16,w/16,512]net = _depthwise_separable_conv(net, 1024, width_multiplier, downsample=True, sc='conv_ds_13')# [batch_size,h/32,w/32,1024]net = _depthwise_separable_conv(net, 1024, width_multiplier, sc='conv_ds_14')# [batch_size,h/32,w/32,1024]net=slim.avg_pool2d(net,[7,7],scope='avg_pool_15') # [batch_size,h/32*7,w/32*7,1024]#end_points=slim.utils.convert_collection_to_dict(end_points_collection)# net=tf.squeeze(net,[1,2],name='SpatialSqueeze')# end_points['squeeze']=net# logits=slim.fully_connected(net,num_classes,activation_fn=None,scope='fc_16')# predictions=slim.softmax(logits,scope='Predictions')## end_points['Logits']=logits# end_points['Predictions']=predictionsf1=end_points['mobilenet/conv_ds_2/pointwise_conv'] #[None,112,112,64]f2=end_points['mobilenet/conv_ds_4/pointwise_conv']#[None,56,56,128]f3=end_points['mobilenet/conv_ds_6/pointwise_conv'] #[None,28,28,256]f4=end_points['mobilenet/conv_ds_12/pointwise_conv']  #[None.14,14,512]f5=end_points['mobilenet/conv_ds_14/pointwise_conv']return inputs,  [f1 , f2 , f3 , f4 , f5 ]
mobilenet.default_image_size = 224def mobilenet_arg_scope(weight_decay=0.0):"""定义默认的scope参数:param weight_decay:  正则的衰减率:return:"""with slim.arg_scope([slim.convolution2d, slim.separable_convolution2d],weights_initializer=slim.initializers.xavier_initializer(),biases_initializer=slim.init_ops.zeros_initializer(),weights_regularizer=slim.l2_regularizer(weight_decay)) as sc:return scif __name__ == '__main__':batch_size = 5height, width = 224, 224num_classes = 100sess = tf.InteractiveSession()sess.run(tf.global_variables_initializer())inputs = tf.random_uniform((batch_size, height, width, 3))inputs_2,  [f1 , f2 , f3 , f4 , f5 ] = mobilenet(inputs, num_classes)

打印出f1,f2,f3,f4,f5的shape

f1: Tensor("mobilenet/conv_ds_2/pointwise_conv/BiasAdd:0", shape=(5, 112, 112, 64), dtype=float32)
f2: Tensor("mobilenet/conv_ds_4/pointwise_conv/BiasAdd:0", shape=(5, 56, 56, 128), dtype=float32)
f3: Tensor("mobilenet/conv_ds_6/pointwise_conv/BiasAdd:0", shape=(5, 28, 28, 256), dtype=float32)
f4: Tensor("mobilenet/conv_ds_12/pointwise_conv/BiasAdd:0", shape=(5, 14, 14, 512), dtype=float32)
f5: Tensor("mobilenet/conv_ds_14/pointwise_conv/BiasAdd:0", shape=(5, 7, 7, 1024), dtype=float32)

PSPnet部分的代码

pspnet_model.py

import tensorflow as tf
from tensorflow.contrib import  slim
from nets.mobilenet_v1 import mobilenet_v1 as  get_mobilenet_encoder
import  numpy as np#
# MERGE_AXIS = -1 # 通道维度上链接def resize_image(input_images,s):""":param input_images: 4D tensor:param s: 缩放比例 （2，2） # 扩大的倍数:return:"""h,w=input_images.get_shape().as_list()[1],input_images.get_shape().as_list()[2]h_ratio=s[0]w_ration=s[1]h=int(h*h_ratio)w=int(w*w_ration)images=tf.image.resize_images(input_images,size=(h,w))return images#进场不同尺度池化的操作
def pool_block( x , pool_factor ,IMAGE_ORDERING = 'NHWC'):""":param x: 4D （1，224，224，3）:param pool_factor: 2 池化的尺度:return:"""if IMAGE_ORDERING == 'NHWC':h, w = x.get_shape().as_list()[1], x.get_shape().as_list()[2]elif IMAGE_ORDERING == 'NCHW':h, w = x.get_shape().as_list()[2], x.get_shape().as_list()[3]# strides = [18,18],[9,9],[6,6],[3,3]pool_size = [int(np.round( float(h) /  pool_factor)), int(np.round(  float(w )/  pool_factor))]strides=pool_size# 进行不同程度的平均x=slim.avg_pool2d(x,kernel_size=pool_size,stride=strides,  padding='SAME') # [1,2,2,3]# x = AveragePooling2D(pool_size , data_format=IMAGE_ORDERING , strides=strides, padding='same')( feats )## 进行卷积x=slim.conv2d(x,512,kernel_size=(1,1),stride=1,padding='SAME') #[1,2,2,512]# x = Conv2D(512, (1 ,1 ), data_format=IMAGE_ORDERING , padding='same' , use_bias=False )( x )x=slim.batch_norm(x)# x = BatchNormalization()(x)# x=slim.relu(x)x=tf.nn.relu(x)# x = Activation('relu' )(x)x=resize_image( x , strides)# x = resize_image( x , strides , data_format=IMAGE_ORDERING )return xdef pspnet(input_images,num_classes,input_height=576, input_width=576):assert input_height%192 == 0assert input_width%192 == 0img_input , levels = get_mobilenet_encoder(inputs=input_images,num_classes=num_classes)[f1 , f2 , f3 , f4 , f5 ] = levels o = f5# 对f5进行不同程度的池化pool_factors = [ 1,2,3,6]pool_outs = [o ]for p in pool_factors:pooled = pool_block(  o , p  )pool_outs.append( pooled )# 连接o=tf.concat(pool_outs,axis=-1)# o = Concatenate( axis=MERGE_AXIS)(pool_outs )o=slim.conv2d(o,512,kernel_size=(1,1),stride=1,padding='SAME')# o = ( Conv2D(512, (1, 1), padding='valid', data_format=IMAGE_ORDERING))(o)o=slim.batch_norm(o)# o = ( BatchNormalization())(o)o=resize_image(o,(2,2))# o = resize_image(o,(2,2),data_format=IMAGE_ORDERING)o=tf.concat([o,f4],axis=-1)# o = Concatenate( axis=MERGE_AXIS)([o,f4])o = slim.conv2d(o,512, kernel_size=(1, 1), stride=1, padding='SAME')# o = ( Conv2D(512, (1, 1), padding='valid', data_format=IMAGE_ORDERING))(o)o = slim.batch_norm(o)# o = ( BatchNormalization())(o)# o = Activation('relu' )(o)o=tf.nn.relu(o)pool_outs = [o]# 对f4进行不同程度的池化for p in pool_factors:pooled = pool_block(  o , p  )pool_outs.append( pooled )# 连接o = tf.concat(pool_outs, axis=-1)# o = Concatenate( axis=MERGE_AXIS)(pool_outs )o = slim.conv2d(o, 512, kernel_size=(1, 1), stride=1, padding='SAME')# o = ( Conv2D(512, (1, 1), padding='valid', data_format=IMAGE_ORDERING))(o)# o = ( BatchNormalization())(o)o=slim.batch_norm(o)o = resize_image(o,(2,2))o = tf.concat([o, f3], axis=-1)# o = Concatenate( axis=MERGE_AXIS)([o,f3])o = slim.conv2d(o, 512, kernel_size=(1, 1), stride=1, padding='SAME')# o = ( Conv2D(512, (1, 1), padding='valid', data_format=IMAGE_ORDERING))(o)o = slim.batch_norm(o)# o = ( BatchNormalization())(o)# o = Activation('relu' )(o)o = tf.nn.relu(o)pool_outs = [o ]# 对f3进行不同程度的池化for p in pool_factors:pooled = pool_block(  o , p  )pool_outs.append( pooled )# 连接o = tf.concat(pool_outs, axis=-1)# o = Concatenate( axis=MERGE_AXIS)(pool_outs )# 卷积o = slim.conv2d(o, 512, kernel_size=(1, 1), stride=1, padding='SAME')# o = Conv2D(512, (1,1), data_format=IMAGE_ORDERING, use_bias=False )(o)o = slim.batch_norm(o)# o = ( BatchNormalization())(o)# o = Activation('relu' )(o)o = tf.nn.relu(o)# 此时输出为[144,144,nclasses]o=slim.conv2d(o,num_classes,kernel_size=(3,3),stride=1,padding='SAME')# o = Conv2D( n_classes,(3,3),data_format=IMAGE_ORDERING, padding='same' )(o)o = resize_image(o,(2,2))# print('o shape',o.get_shape())o=tf.reshape(o,(-1,(input_height*input_width)//16,num_classes))# o=slim.softmax(o)# o = Reshape((-1,n_classes))(o)# o = Softmax()(o)# model = Model(img_input,o)out_put=oreturn out_putif __name__ == '__main__':input_images=tf.ones((1,576,576,3),dtype=tf.float32)# images=resize_image(input_images,s=(2,2))out_put=pspnet(input_images,num_classes=100,input_height=576, input_width=576)

tensorflow系列之_pspnet网络相关推荐

【TensorFlow系列一】TensorFlow工作原理
↑ 点击上方[计算机视觉联盟]关注我们今天开始,小编会更新TensorFlow系列文章,包括TensorFlow的使用和TensorFlow实践的项目等. 本篇主要介绍TensorFlow的计算模型 ...
首次运行 tensorflow 项目之 vgg 网络
首次运行 tensorflow 项目之 vgg 网络文章目录 1. 下载所需文件 2. 在 pycharm 中打开项目 3. 为项目设置 python 编译器 4. 调试代码 1. train.py ...
Alamofire源码解读系列(七)之网络监控(NetworkReachabilityManager)
Alamofire源码解读系列(七)之网络监控(NetworkReachabilityManager) 本篇主要讲解iOS开发中的网络监控前言在开发中,有时候我们需要获取这些信息: 手机是否联网 ...
K8s系列之：网络原理
K8s系列之:网络原理一.K8s网络模型二.Docker的网络模型三.网络的命名空间 1.网络命名空间的实现 2.网络命名空间的操作 3.网络命名空间的一些技巧四.Veth设备对 1.Veth ...
利用TensorFlow搭建CNN,DNN网络实现图像手写识别，总结。
利用TensorFlow搭建CNN,DNN网络实现图像手写识别,总结. 摘要一.神经网络与卷积网络的对比 1.数据处理 2.对获取到的数据进行归一化和独热编码二.开始我们的tensorflow神经 ...
TensorFlow 系列案例（3）：使用TensorFlow DNN分类器对数据进行分类
TensorFlow 卷积神经网络系列案例(1):猫狗识别 https://blog.csdn.net/duan_zhihua/article/details/81156693 TensorFlow ...
Docker重学系列之高级网络篇
Docker重学系列之高级网络篇高级网络配置说明 veth-pair技术网络小结 Docker 网络相关的命令列表容器访问控制容器访问外部网络容器之间访问访问所有端口访问指定端口映射 ...
深入理解DeepLab系列语义分割网络
语义分割是指在像素级别上进行分类,从而转换得到感兴趣区域的掩膜.说起语义分割的发展则肯定绕不开DeepLab系列语义分割网络,该系列网络由谷歌团队提出并发展,在VOC2012等公用语义分割数据集上,取 ...
DeepLab大盘点 | 深入理解DeepLab系列语义分割网络
作者 | 深蓝AI 编辑 | 汽车人点击下方卡片,关注"自动驾驶之心"公众号 ADAS巨卷干货,即可获取点击进入→自动驾驶之心技术交流群后台回复[分割综述]获取语义分割.实 ...

tensorflow系列之_pspnet网络

tensorflow系列之_pspnet网络相关推荐

最新文章

热门文章