yolov1代码详解

最新推荐文章于 2025-03-26 17:33:04 发布

路上的病人

最新推荐文章于 2025-03-26 17:33:04 发布

阅读量3.8k

点赞数 1

CC 4.0 BY-SA版权

分类专栏： Tensorflow学习之路文章标签： yolo tensorflow

本文链接：https://blog.youkuaiyun.com/qq_40994943/article/details/85401803

本文详细探讨了YOLOv1网络的实现代码，包括关键部分的讲解，并鼓励读者通过留言与作者共同探讨可能存在的疑问。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

有不懂的可留言和笔者讨论，有些笔者也还有疑问

yolo_net.py

import numpy as np
import tensorflow as tf
import yolo.config as cfg

slim = tf.contrib.slim


class YOLONet(object):

    def __init__(self, is_training=True):
        self.classes = cfg.CLASSES
        self.num_class = len(self.classes)
        self.image_size = cfg.IMAGE_SIZE
        self.cell_size = cfg.CELL_SIZE
        self.boxes_per_cell = cfg.BOXES_PER_CELL
        self.output_size = (self.cell_size * self.cell_size) * (self.num_class + self.boxes_per_cell * 5)
        self.scale = 1.0 * self.image_size / self.cell_size
        self.boundary1 = self.cell_size * self.cell_size * self.num_class  # 7*7*20
        self.boundary2 = self.boundary1 + self.cell_size * self.cell_size * self.boxes_per_cell  # +7*7*2

        self.object_scale = cfg.OBJECT_SCALE
        self.noobject_scale = cfg.NOOBJECT_SCALE
        self.class_scale = cfg.CLASS_SCALE
        self.coord_scale = cfg.COORD_SCALE

        self.learning_rate = cfg.LEARNING_RATE
        self.batch_size = cfg.BATCH_SIZE
        self.alpha = cfg.ALPHA

        self.offset = np.transpose(np.reshape(np.array(
            [np.arange(self.cell_size)] * self.cell_size * self.boxes_per_cell),
            (self.boxes_per_cell, self.cell_size, self.cell_size)), (1, 2, 0))

        self.images = tf.placeholder(
            tf.float32, [None, self.image_size, self.image_size, 3],
            name='images')
        self.logits = self.build_network(
            self.images, num_outputs=self.output_size, alpha=self.alpha,
            is_training=is_training)

        if is_training:
            self.labels = tf.placeholder(
                tf.float32,
                [None, self.cell_size, self.cell_size, 5 + self.num_class])
            self.loss_layer(self.logits, self.labels)
            self.total_loss = tf.losses.get_total_loss()
            tf.summary.scalar('total_loss', self.total_loss)

    def build_network(self,
                      images,
                      num_outputs,
                      alpha,
                      keep_prob=0.5,
                      is_training=True,
                      scope='yolo'):
        #定义结构，输出7*7*30张量
        with tf.variable_scope(scope):
            with slim.arg_scope(
                [slim.conv2d, slim.fully_connected],
                activation_fn=leaky_relu(alpha),
                weights_regularizer=slim.l2_regularizer(0.0005),
                weights_initializer=tf.truncated_normal_initializer(0.0, 0.01)
            ):
                net = tf.pad(
                    images, np.array([[0, 0], [3, 3], [3, 3], [0, 0]]),
                    name='pad_1')
                net = slim.conv2d(
                    net, 64, 7, 2, padding='VALID', scope='conv_2')
                net = slim.max_pool2d(net, 2, padding='SAME', scope='pool_3')
                net = slim.conv2d(net, 192