版权声明：如使用此博客内容，请经过作者同意，谢谢 https://blog.csdn.net/qq_40994943/article/details/85401803
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, 3, scope='conv_4')
net = slim.max_pool2d(net, 2, padding='SAME', scope='pool_5')
net = slim.conv2d(net, 128, 1, scope='conv_6')
net = slim.conv2d(net, 256, 3, scope='conv_7')
net = slim.conv2d(net, 256, 1, scope='conv_8')
net = slim.conv2d(net, 512, 3, scope='conv_9')
net = slim.max_pool2d(net, 2, padding='SAME', scope='pool_10')
net = slim.conv2d(net, 256, 1, scope='conv_11')
net = slim.conv2d(net, 512, 3, scope='conv_12')
net = slim.conv2d(net, 256, 1, scope='conv_13')
net = slim.conv2d(net, 512, 3, scope='conv_14')
net = slim.conv2d(net, 256, 1, scope='conv_15')
net = slim.conv2d(net, 512, 3, scope='conv_16')
net = slim.conv2d(net, 256, 1, scope='conv_17')
net = slim.conv2d(net, 512, 3, scope='conv_18')
net = slim.conv2d(net, 512, 1, scope='conv_19')
net = slim.conv2d(net, 1024, 3, scope='conv_20')
net = slim.max_pool2d(net, 2, padding='SAME', scope='pool_21')
net = slim.conv2d(net, 512, 1, scope='conv_22')
net = slim.conv2d(net, 1024, 3, scope='conv_23')
net = slim.conv2d(net, 512, 1, scope='conv_24')
net = slim.conv2d(net, 1024, 3, scope='conv_25')
net = slim.conv2d(net, 1024, 3, scope='conv_26')
net = tf.pad(
net, np.array([[0, 0], [1, 1], [1, 1], [0, 0]]),
name='pad_27')
net = slim.conv2d(
net, 1024, 3, 2, padding='VALID', scope='conv_28')
net = slim.conv2d(net, 1024, 3, scope='conv_29')
net = slim.conv2d(net, 1024, 3, scope='conv_30')
net = tf.transpose(net, [0, 3, 1, 2], name='trans_31')
net = slim.flatten(net, scope='flat_32')
net = slim.fully_connected(net, 512, scope='fc_33')
net = slim.fully_connected(net, 4096, scope='fc_34')
net = slim.dropout(
net, keep_prob=keep_prob, is_training=is_training,
scope='dropout_35')
net = slim.fully_connected(
net, num_outputs, activation_fn=None, scope='fc_36')
return net
#计算iou值
def calc_iou(self, boxes1, boxes2, scope='iou'):
"""calculate ious
Args:
boxes1: 5-D tensor [BATCH_SIZE, CELL_SIZE, CELL_SIZE, BOXES_PER_CELL, 4] ====> (x_center, y_center, w, h)
boxes2: 5-D tensor [BATCH_SIZE, CELL_SIZE, CELL_SIZE, BOXES_PER_CELL, 4] ===> (x_center, y_center, w, h)
Return:
iou: 4-D tensor [BATCH_SIZE, CELL_SIZE, CELL_SIZE, BOXES_PER_CELL]
"""
with tf.variable_scope(scope):
# transform (x_center, y_center, w, h) to (x1, y1, x2, y2)
boxes1_t = tf.stack([boxes1[..., 0] - boxes1[..., 2] / 2.0,
boxes1[..., 1] - boxes1[..., 3] / 2.0, # 算出框的边界值，自己在纸上画两个框就能懂
boxes1[..., 0] + boxes1[..., 2] / 2.0,
boxes1[..., 1] + boxes1[..., 3] / 2.0],
axis=-1)
boxes2_t = tf.stack([boxes2[..., 0] - boxes2[..., 2] / 2.0,
boxes2[..., 1] - boxes2[..., 3] / 2.0,
boxes2[..., 0] + boxes2[..., 2] / 2.0,
boxes2[..., 1] + boxes2[..., 3] / 2.0],
axis=-1)
# calculate the left up point & right down point左上角和右下角点
lu = tf.maximum(boxes1_t[..., :2], boxes2_t[..., :2])
rd = tf.minimum(boxes1_t[..., 2:], boxes2_t[..., 2:])
# intersection
intersection = tf.maximum(0.0, rd - lu)
inter_square = intersection[..., 0] * intersection[..., 1]# S 交
# calculate the boxs1 square and boxs2 square
square1 = boxes1[..., 2] * boxes1[..., 3]#S box1
square2 = boxes2[..., 2] * boxes2[..., 3]
union_square = tf.maximum(square1 + square2 - inter_square, 1e-10)#S 并
return tf.clip_by_value(inter_square / union_square, 0.0, 1.0)
def loss_layer(self, predicts, labels, scope='loss_layer'):
# predicts：Yolo网络的输出形状[None, 1470]
# 0：7 * 7 * 20：表示预测类别
# 7 * 7 * 20: 7 * 7 * 20 + 7 * 7 * 2:表示预测置信度，即预测的边界框与实际边界框之间的IOU
# 7 * 7 * 20 + 7 * 7 * 2：1470：预测边界框(xywh*2)
# 目标中心是相对于当前格子的，宽度和高度的开根号是相对当前整张图像的(归一化的)
# labels：标签值
# 形状[None, 7, 7, 25]
# 0: 1：置信度，表示这个地方是否有目标
# 1: 5：目标边界框
# 目标中心，宽度和高度(没有归一化)
# 5: 25：目标的类别
with tf.variable_scope(scope):
predict_classes = tf.reshape( # 预测每个格子目标的类别 形状[45,7,7,20]
predicts[:, :self.boundary1],
[self.batch_size, self.cell_size, self.cell_size, self.num_class])
predict_scales = tf.reshape(
predicts[:, self.boundary1:self.boundary2], # 预测每个格子中两个边界框的置信度 形状[45,7,7,2]
[self.batch_size, self.cell_size, self.cell_size, self.boxes_per_cell])
predict_boxes = tf.reshape(
predicts[:, self.boundary2:], # 预测每个格子中的两个边界框，(x,y)表示边界框相对于格子边界框的中心 w,h的开根号相对于整个图片
[self.batch_size, self.cell_size, self.cell_size, self.boxes_per_cell, 4]) # 形状[45,7,7,2,4]
response = tf.reshape( # 标签的置信度,表示这个地方是否有目标 形状[45,7,7,1]
labels[..., 0],
[self.batch_size, self.cell_size, self.cell_size, 1])
boxes = tf.reshape( # 标签的边界框 (x,y)表示边界框相对于整个图片的中心 目标坐标 形状[45,7,7,1,4]
labels[..., 1:5],
[self.batch_size, self.cell_size, self.cell_size, 1, 4])
# 标签的边界框 归一化后 张量沿着axis=3重复两边，扩充后[45,7,7,2,4]
boxes = tf.tile(boxes, [1, 1, 1, self.boxes_per_cell, 1]) / self.image_size
classes = labels[..., 5:] # 目标类别
# predict_boxes_tran：offset变量用于把预测边界框predict_boxes中的坐标中心(x, y)
# 由相对当前格子转换为相对当前整个图片
#
# offset，这个是构造的[7, 7, 2]
# 矩阵，每一行都是[7, 2]
# 的矩阵，值为[[0, 0], [1, 1], [2, 2], [3, 3], [4, 4], [5, 5], [6, 6]]
# 这个变量是为了将每个cell的坐标对齐，后一个框比前一个框要多加1
# 比如我们预测了cell_size的每个中心点坐标，那么我们这个中心点落在第几个cell_size
# 就对应坐标要加几，这个用法比较巧妙，构造了这样一个数组，让他们对应位置相加
# offset shape为[1,7,7,2] 如果忽略axis=0，则每一行都是 [[0,0],[1,1],[2,2],[3,3],[4,4],[5,5],[6,6]]
offset = tf.reshape(
tf.constant(self.offset, dtype=tf.float32),
[1, self.cell_size, self.cell_size, self.boxes_per_cell])
# shape为[45,7,7,2]
offset = tf.tile(offset, [self.batch_size, 1, 1, 1])
# shape为[45,7,7,2] 如果忽略axis=0 第i行为[[i,i],[i,i],[i,i],[i,i],[i,i],[i,i],[i,i]]
offset_tran = tf.transpose(offset, (0, 2, 1, 3))
# shape为[45,7,7,2,4] 计算每个格子中的预测边界框坐标(x,y)相对于整个图片的位置 而不是相对当前格子
# 假设当前格子为(3,3)，当前格子的预测边界框为(x0,y0)，则计算坐标(x,y) = ((x0,y0)+(3,3))/7
predict_boxes_tran = tf.stack(
[(predict_boxes[..., 0] + offset) / self.cell_size, # x，除7是指相对于自己格子
(predict_boxes[..., 1] + offset_tran) / self.cell_size, # y
tf.square(predict_boxes[..., 2]), # w
tf.square(predict_boxes[..., 3])], axis=-1) # h
# 计算每个格子预测边界框与真实边界框之间的IOU [45,7,7,2]
iou_predict_truth = self.calc_iou(predict_boxes_tran, boxes)
# calculate I tensor [BATCH_SIZE, CELL_SIZE, CELL_SIZE, BOXES_PER_CELL]
# 这个是求论文中的1ijobj参数，[45,7,7,2] 1ijobj：表示网格单元i的第j个编辑框预测器’负责‘该预测
# 先计算每个框交并比最大的那个，因为我们知道，YOLO每个格子预测两个边界框，一个类别。在训练时，每个目标只需要
# 一个预测器来负责，我们指定一个预测器"负责"，根据哪个预测器与真实值之间具有当前最高的IOU来预测目标。
# 所以object_mask就表示每个格子中的哪个边界框负责该格子中目标预测？哪个边界框取值为1，哪个边界框就负责目标预测
# 当格子中的确有目标时，取值为[1,1]，[1,0],[0,1]
# 比如某一个格子的值为[1,0]，表示第一个边界框负责该格子目标的预测 [0,1]：表示第二个边界框负责该格子目标的预测
# 当格子没有目标时，取值为[0,0]
object_mask = tf.reduce_max(iou_predict_truth, 3, keep_dims=True)
object_mask = tf.cast((iou_predict_truth >= object_mask), tf.float32) * response
# calculate no_I tensor [CELL_SIZE, CELL_SIZE, BOXES_PER_CELL]
# noobject_mask就表示每个边界框不负责该目标的置信度，
# 使用tf.onr_like，使得全部为1,再减去有目标的，也就是有目标的对应坐标为1,这样一减，就变为没有的了。[45,7,7,2]
noobject_mask = tf.ones_like(
object_mask, dtype=tf.float32) - object_mask
# boxes_tran 这个就是把之前的坐标换回来(相对整个图像->相对当前格子)，
# 长和宽开方(原因在论文中有说明)，后面求loss就方便。 shape为(4, 45, 7, 7, 2)
boxes_tran = tf.stack(
[boxes[..., 0] * self.cell_size - offset,
boxes[..., 1] * self.cell_size - offset_tran,
tf.sqrt(boxes[..., 2]),
tf.sqrt(boxes[..., 3])], axis=-1)
# class_loss
# class_loss 分类损失，如果目标出现在网格中 response为1，否则response为0 原文代价函数公式第5项
# 该项表名当格子中有目标时，预测的类别越接近实际类别，代价值越小 原文代价函数公式第5项
class_delta = response * (predict_classes - classes)
class_loss = tf.reduce_mean(
tf.reduce_sum(tf.square(class_delta), axis=[1, 2, 3]),
name='class_loss') * self.class_scale
# object_loss
# object_loss 有目标物体存在的置信度预测损失 原文代价函数公式第3项
# 该项表名当格子中有目标时，负责该目标预测的边界框的置信度越越接近预测的边界框与实际边界框之间的IOU时，代价值越小
object_delta = object_mask * (predict_scales - iou_predict_truth)
object_loss = tf.reduce_mean(
tf.reduce_sum(tf.square(object_delta), axis=[1, 2, 3]),
name='object_loss') * self.object_scale
# noobject_loss没有目标物体存在的置信度的损失(此时iou_predict_truth为0) 原文代价函数公式第4项
# 该项表明当格子中没有目标时，预测的两个边界框的置信度越接近0，代价值越小
noobject_delta = noobject_mask * predict_scales
noobject_loss = tf.reduce_mean(
tf.reduce_sum(tf.square(noobject_delta), axis=[1, 2, 3]),
name='noobject_loss') * self.noobject_scale
# coord_loss边界框坐标损失 shape 为 [batch_size, 7, 7, 2, 1] 原文代价函数公式1,2项
# 该项表名当格子中有目标时，预测的边界框越接近实际边界框，代价值越小
coord_mask = tf.expand_dims(object_mask, 4)
boxes_delta = coord_mask * (predict_boxes - boxes_tran)
coord_loss = tf.reduce_mean(
tf.reduce_sum(tf.square(boxes_delta), axis=[1, 2, 3, 4]),
name='coord_loss') * self.coord_scale
# 将所有损失放在一起
tf.losses.add_loss(class_loss)
tf.losses.add_loss(object_loss)
tf.losses.add_loss(noobject_loss)
tf.losses.add_loss(coord_loss)
# 将每个损失添加到日志记录
tf.summary.scalar('class_loss', class_loss)
tf.summary.scalar('object_loss', object_loss)
tf.summary.scalar('noobject_loss', noobject_loss)
tf.summary.scalar('coord_loss', coord_loss)
tf.summary.histogram('boxes_delta_x', boxes_delta[..., 0])
tf.summary.histogram('boxes_delta_y', boxes_delta[..., 1])
tf.summary.histogram('boxes_delta_w', boxes_delta[..., 2])
tf.summary.histogram('boxes_delta_h', boxes_delta[..., 3])
tf.summary.histogram('iou', iou_predict_truth)
#激活函数
def leaky_relu(alpha):
def op(inputs):
return tf.nn.leaky_relu(inputs, alpha=alpha, name='leaky_relu')
return op
参考：blog