MTCNN开源训练（PNet训练）

最新推荐文章于 2024-05-27 09:45:57 发布

小白的深度学习之路

最新推荐文章于 2024-05-27 09:45:57 发布

阅读量4.6k

点赞数 2

分类专栏： MTCNN系列

本文链接：https://blog.csdn.net/weixin_43198141/article/details/89532426

版权

本文介绍了MTCNN中的PNet结构，它是一个全卷积网络。PNet训练过程包括从tfrecord中读取数据，定义优化器和占位符，计算损失、准确率和摘要操作，初始化变量并构建会话。训练时需注意数据处理，因某些图像处理函数只能处理单张图片，需对batch数据进行逐张处理。提供了PNet的训练代码供参考。

摘要由CSDN通过智能技术生成

PNet结构简介
PNet是一个全卷积网络，具体结构如下
在这里插入图片描述
代码如下：

def P_Net(inputs,label=None,bbox_target=None,landmark_target=None,training=True):
    #define common param
    with slim.arg_scope([slim.conv2d],
                        activation_fn=prelu,
                        weights_initializer=slim.xavier_initializer(),
                        biases_initializer=tf.zeros_initializer(),
                        weights_regularizer=slim.l2_regularizer(0.0005), 
                        padding='valid'):
        print(inputs.get_shape())

        net = slim.conv2d(inputs, 10, 3, stride=1,scope='conv1')
        _activation_summary(net)
        print(net.get_shape())
        net = slim.max_pool2d(net, kernel_size=[2,2], stride=2, scope='pool1', padding='SAME')
        _activation_summary(net)
        print(net.get_shape())
        net = slim.conv2d(net,num_outputs=16,kernel_size=[3,3],stride=1,scope='conv2')
        _activation_summary(net)
        print(net.get_shape())
        #
        net = slim.conv2d(net,num_outputs=32,kernel_size=[3,3],stride=1,scope='conv3')
        _activation_summary(net)
        print(net.get_shape())
        #batch*H*W*2
        conv4_1 = slim.conv2d(net,num_outputs=2,kernel_size=[1,1],stride=1,scope='conv4_1',activation_fn=tf.nn.softmax)
        _activation_summary(conv4_1)
        #conv4_1 = slim.conv2d(net,num_outputs=1,kernel_size=[1,1],stride=1,scope='conv4_1',activation_fn=tf.nn.sigmoid)
        
        print (conv4_1.get_shape())
        #batch*H*W*4
        bbox_pred = slim.conv2d(net,num_outputs=4,kernel_size=[1,1],stride=1,scope='conv4_2',activation_fn=None)
        _activation_summary(bbox_pred)
        print (bbox_pred.get_shape())
        #batch*H*W*10
        landmark_pred = slim.conv2d(net,num_outputs=10,kernel_size=[1,1],stride=1,scope='conv4_3',activation_fn=None)
        _activation_summary(landmark_pred)
        print (landmark_pred.get_shape())
        # add projectors for visualization
        #cls_prob_original = conv4_1 
        #bbox_pred_original = bbox_pred
        if training:
            #batch*2
            # calculate classification loss
            cls_prob = tf.squeeze(conv4_1,[1,2],name='cls_prob')
            cls_loss = cls_ohem(cls_prob,label)
            #batch
            # cal bounding box er