1.计算anchor的iou
计算九个anchor框和真实框的iou
2.计算网格位置
3.填充正样本
把真实样本的信息填充到target里面去
4.删选负样本
把不是负样本的删除掉，否则负样本太多
1.遍历Yolo Head（78，38，19）
2.构造掩码
mask:[1,3,19,19]=0 正样本掩码，首先全赋值为0，如果为正样本，则赋值为1
noobj_mask: [1,3,19,19]=1 负样本掩码，首先全赋值为1，假设没有物体，全是负样本，然后赋值为0
tbox:[1,3,19,19, 4] =0
tconf:[1,3,19,19] = 0
tcls::[1,3,19,19,num_Class] =0
3.记录当前head对应的3个anchors的绝对序号
4.计算真实label和9个anchors的iou,找出序号
找出序号，计算相对位置，用来计算网格位置i,j
5.填充掩码
填充掩码，一定要有i,j和相对anchor序号，i,j通过target获得，相对序号通过anchors和target共同获得
1.通过target，获得ij
2.通过target和anchors，计算iou,取最大iou，获得绝对的anchor序号，进而计算出相对序号
3.通过ij和相对序号，进行掩码填充
6.删选负样本，将摇摆不定的正样本和负样本之间的样本删除，使之不参与损失的计算
获得预测值
1.预测值和target计算他们之间的iou
2.通过阈值删选iou,删除摇摆不定的样本
3.获得负样本的掩码
返回预测值和负样本掩码
import cv2
from random import shuffle
import numpy as np
import torch
import torch.nn as nn
import math
import torch.nn.functional as F
from matplotlib.colors import rgb_to_hsv, hsv_to_rgb
from PIL import Image
from utils.utils import bbox_iou, merge_bboxes
def iou(_box_a, _box_b):
b1_x1, b1_x2 = _box_a[:, 0] - _box_a[:, 2] / 2, _box_a[:, 0] + _box_a[:, 2] / 2
b1_y1, b1_y2 = _box_a[:, 1] - _box_a[:, 3] / 2, _box_a[:, 1] + _box_a[:, 3] / 2
b2_x1, b2_x2 = _box_b[:, 0] - _box_b[:, 2] / 2, _box_b[:, 0] + _box_b[:, 2] / 2
b2_y1, b2_y2 = _box_b[:, 1] - _box_b[:, 3] / 2, _box_b[:, 1] + _box_b[:, 3] / 2
box_a = torch.zeros_like(_box_a)
box_b = torch.zeros_like(_box_b)
box_a[:, 0], box_a[:, 1], box_a[:, 2], box_a[:, 3] = b1_x1, b1_y1, b1_x2, b1_y2
box_b[:, 0], box_b[:, 1], box_b[:, 2], box_b[:, 3] = b2_x1, b2_y1, b2_x2, b2_y2
A = box_a.size(0)
B = box_b.size(0)
max_xy = torch.min(box_a[:, 2:].unsqueeze(1).expand(A, B, 2),
box_b[:, 2:].unsqueeze(0).expand(A, B, 2))
min_xy = torch.max(box_a[:, :2].unsqueeze(1).expand(A, B, 2),
box_b[:, :2].unsqueeze(0).expand(A, B, 2))
inter = torch.clamp((max_xy - min_xy), min=0)
inter = inter[:, :, 0] * inter[:, :, 1]
# 计算先验框和真实框各自的面积
area_a = ((box_a[:, 2]-box_a[:, 0]) *
(box_a[:, 3]-box_a[:, 1])).unsqueeze(1).expand_as(inter) # [A,B]
area_b = ((box_b[:, 2]-box_b[:, 0]) *
(box_b[:, 3]-box_b[:, 1])).unsqueeze(0).expand_as(inter) # [A,B]
# 求IOU
union = area_a + area_b - inter
return inter / union # [A,B]
#---------------------------------------------------#
# 平滑标签
#---------------------------------------------------#
def smooth_labels(y_true, label_smoothing,num_classes):
return y_true * (1.0 - label_smoothing) + label_smoothing / num_classes
def box_ciou(b1, b2):
"""
输入为：
----------
b1: tensor, shape=(batch, feat_w, feat_h, anchor_num, 4), xywh
b2: tensor, shape=(batch, feat_w, feat_h, anchor_num, 4), xywh
返回为：
-------
ciou: tensor, shape=(batch, feat_w, feat_h, anchor_num, 1)
"""
# 求出预测框左上角右下角
b1_xy = b1[..., :2]
b1_wh = b1[..., 2:4]
b1_wh_half = b1_wh/2.
b1_mins = b1_xy - b1_wh_half
b1_maxes = b1_xy + b1_wh_half
# 求出真实框左上角右下角
b2_xy = b2[..., :2]
b2_wh = b2[..., 2:4]
b2_wh_half = b2_wh/2.
b2_mins = b2_xy - b2_wh_half
b2_maxes = b2_xy + b2_wh_half
# 求真实框和预测框所有的iou
intersect_mins = torch.max(b1_mins, b2_mins)
intersect_maxes = torch.min(b1_maxes, b2_maxes)
intersect_wh = torch.max(intersect_maxes - intersect_mins, torch.zeros_like(intersect_maxes))
intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
b1_area = b1_wh[..., 0] * b1_wh[..., 1]
b2_area = b2_wh[..., 0] * b2_wh[..., 1]
union_area = b1_area + b2_area - intersect_area
iou = intersect_area / torch.clamp(union_area,min = 1e-6)
# 计算中心的差距
center_distance = torch.sum(torch.pow((b1_xy - b2_xy), 2), axis=-1)
# 找到包裹两个框的最小框的左上角和右下角
enclose_mins = torch.min(b1_mins, b2_mins)
enclose_maxes = torch.max(b1_maxes, b2_maxes)
enclose_wh = torch.max(enclose_maxes - enclose_mins, torch.zeros_like(intersect_maxes))
# 计算对角线距离
enclose_diagonal = torch.sum(torch.pow(enclose_wh,2), axis=-1)
ciou = iou - 1.0 * (center_distance) / torch.clamp(enclose_diagonal,min = 1e-6)
v = (4 / (math.pi ** 2)) * torch.pow((torch.atan(b1_wh[..., 0]/torch.clamp(b1_wh[..., 1],min = 1e-6)) - torch.atan(b2_wh[..., 0]/torch.clamp(b2_wh[..., 1],min = 1e-6))), 2)
alpha = v / torch.clamp((1.0 - iou + v),min=1e-6)
ciou = ciou - alpha * v
return ciou
def clip_by_tensor(t,t_min,t_max):
t=t.float()
result = (t >= t_min).float() * t + (t < t_min).float() * t_min
result = (result <= t_max).float() * result + (result > t_max).float() * t_max
return result
def MSELoss(pred,target):
return (pred-target)**2
def BCELoss(pred,target):
epsilon = 1e-7
pred = clip_by_tensor(pred, epsilon, 1.0 - epsilon)
output = -target * torch.log(pred) - (1.0 - target) * torch.log(1.0 - pred)
return output
class YOLOLoss(nn.Module):
def __init__(self, anchors, num_classes, img_size, label_smooth=0, cuda=True):
super(YOLOLoss, self).__init__()
self.anchors = anchors
self.num_anchors = len(anchors)
self.num_classes = num_classes
self.bbox_attrs = 5 + num_classes
self.img_size = img_size
self.feature_length = [img_size[0]//8,img_size[0]//16,img_size[0]//32]
self.label_smooth = label_smooth
self.ignore_threshold = 0.7
self.lambda_conf = 1.0
self.lambda_cls = 1.0
self.lambda_loc = 1.0
self.cuda = cuda
def forward(self, input, targets=None):
# input为bs,3*(5+num_classes),13,13
# 一共多少张图片
bs = input.size(0)
# 特征层的高
in_h = input.size(2)
# 特征层的宽
in_w = input.size(3)
# 计算步长
# 每一个特征点对应原来的图片上多少个像素点
# 如果特征层为13x13的话，一个特征点就对应原来的图片上的32个像素点
stride_h = self.img_size[1] / in_h
stride_w = self.img_size[0] / in_w
# 把先验框的尺寸调整成特征层大小的形式
# 计算出先验框在特征层上对应的宽高
scaled_anchors = [(a_w / stride_w, a_h / stride_h) for a_w, a_h in self.anchors]
# bs,3*(5+num_classes),13,13 -> bs,3,13,13,(5+num_classes)
prediction = input.view(bs, int(self.num_anchors/3),
self.bbox_attrs, in_h, in_w).permute(0, 1, 3, 4, 2).contiguous()
# 对prediction预测进行调整
conf = torch.sigmoid(prediction[..., 4]) # Conf
pred_cls = torch.sigmoid(prediction[..., 5:]) # Cls pred.
# 找到哪些先验框内部包含物体
mask, noobj_mask, t_box, tconf, tcls, box_loss_scale_x, box_loss_scale_y = self.get_target(targets, scaled_anchors,in_w, in_h,self.ignore_threshold)
noobj_mask, pred_boxes_for_ciou = self.get_ignore(prediction, targets, scaled_anchors, in_w, in_h, noobj_mask)
if self.cuda:
mask, noobj_mask = mask.cuda(), noobj_mask.cuda()
box_loss_scale_x, box_loss_scale_y= box_loss_scale_x.cuda(), box_loss_scale_y.cuda()
tconf, tcls = tconf.cuda(), tcls.cuda()
pred_boxes_for_ciou = pred_boxes_for_ciou.cuda()
t_box = t_box.cuda()
box_loss_scale = 2-box_loss_scale_x*box_loss_scale_y
# losses.
ciou = box_ciou( pred_boxes_for_ciou[mask.bool()], t_box[mask.bool()])
loss_ciou = 1 - ciou
loss_ciou = loss_ciou * box_loss_scale[mask.bool()]
# ciou = (1 - box_ciou( pred_boxes_for_ciou[mask.bool()], t_box[mask.bool()]))* box_loss_scale[mask.bool()]
loss_loc = torch.sum(loss_ciou / bs)
loss_conf = torch.sum(BCELoss(conf, mask) * mask / bs) + \
torch.sum(BCELoss(conf, mask) * noobj_mask / bs)
# print(smooth_labels(tcls[mask == 1],self.label_smooth,self.num_classes))
loss_cls = torch.sum(BCELoss(pred_cls[mask == 1], smooth_labels(tcls[mask == 1],self.label_smooth,self.num_classes))/bs)
# print(loss_loc,loss_conf,loss_cls)
loss = loss_conf * self.lambda_conf + loss_cls * self.lambda_cls + loss_loc * self.lambda_loc
return loss, loss_conf.item(), loss_cls.item(), loss_loc.item()
def get_target(self, target, anchors, in_w, in_h, ignore_threshold):
# 计算一共有多少张图片
bs = len(target)
# 获得先验框
anchor_index = [[0,1,2],[3,4,5],[6,7,8]][self.feature_length.index(in_w)]
subtract_index = [0,3,6][self.feature_length.index(in_w)]
# 创建全是0或者全是1的阵列
mask = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, requires_grad=False)
noobj_mask = torch.ones(bs, int(self.num_anchors/3), in_h, in_w, requires_grad=False)
tx = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, requires_grad=False)
ty = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, requires_grad=False)
tw = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, requires_grad=False)
th = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, requires_grad=False)
t_box = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, 4, requires_grad=False)
tconf = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, requires_grad=False)
tcls = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, self.num_classes, requires_grad=False)
box_loss_scale_x = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, requires_grad=False)
box_loss_scale_y = torch.zeros(bs, int(self.num_anchors/3), in_h, in_w, requires_grad=False)
for b in range(bs):
for t in range(target[b].shape[0]):
# box = [0.2,0.7,0.25,0.4] ---> [gx,gh,gw,gh] 相对于图的偏移,就是原图608*608 / 608 = 1 * 1 ===》 0.2*608 0.7*608 0.25*608
# box = box * 19 = [3.8,13.3,4.75,7.6]
# i = int(3.8)=3 j = int(13.3) =13
# 计算出在特征层上的点位
gx = target[b][t, 0] * in_w
gy = target[b][t, 1] * in_h
gw = target[b][t, 2] * in_w
gh = target[b][t, 3] * in_h
# 计算出属于哪个网格
gi = int(gx)
gj = int(gy)
# 计算真实框的位置
gt_box = torch.FloatTensor(np.array([0, 0, gw, gh])).unsqueeze(0)
# 计算出所有先验框的位置
anchor_shapes = torch.FloatTensor(np.concatenate((np.zeros((self.num_anchors, 2)),
np.array(anchors)), 1))
# 计算重合程度
anch_ious = bbox_iou(gt_box, anchor_shapes)
# Find the best matching anchor box
# 计算真实label和9个anchors的IOU,找出序号
# 假定best_n = 6,那么就落在19的Head上，对应的相对位置是0
best_n = np.argmax(anch_ious)
if best_n not in anchor_index:
continue
# Masks
if (gj < in_h) and (gi < in_w):
best_n = best_n - subtract_index
# 判定哪些先验框内部真实的存在物体
noobj_mask[b, best_n, gj, gi] = 0
mask[b, best_n, gj, gi] = 1
# 计算先验框中心调整参数
tx[b, best_n, gj, gi] = gx
ty[b, best_n, gj, gi] = gy
# 计算先验框宽高调整参数
tw[b, best_n, gj, gi] = gw
th[b, best_n, gj, gi] = gh
# 用于获得xywh的比例
box_loss_scale_x[b, best_n, gj, gi] = target[b][t, 2]
box_loss_scale_y[b, best_n, gj, gi] = target[b][t, 3]
# 物体置信度
tconf[b, best_n, gj, gi] = 1
# 种类
tcls[b, best_n, gj, gi, int(target[b][t, 4])] = 1
else:
print('Step {0} out of bound'.format(b))
print('gj: {0}, height: {1} | gi: {2}, width: {3}'.format(gj, in_h, gi, in_w))
continue
t_box[...,0] = tx
t_box[...,1] = ty
t_box[...,2] = tw
t_box[...,3] = th
return mask, noobj_mask, t_box, tconf, tcls, box_loss_scale_x, box_loss_scale_y
def get_ignore(self,prediction,target,scaled_anchors,in_w, in_h,noobj_mask):
bs = len(target)
anchor_index = [[0,1,2],[3,4,5],[6,7,8]][self.feature_length.index(in_w)]
scaled_anchors = np.array(scaled_anchors)[anchor_index]
# 先验框的中心位置的调整参数
x = torch.sigmoid(prediction[..., 0])
y = torch.sigmoid(prediction[..., 1])
# 先验框的宽高调整参数
w = prediction[..., 2] # Width
h = prediction[..., 3] # Height
FloatTensor = torch.cuda.FloatTensor if x.is_cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if x.is_cuda else torch.LongTensor
# 生成网格，先验框中心，网格左上角
# grid_x = [1,3,19,19]
# grid_y = [1,3,19,19]
grid_x = torch.linspace(0, in_w - 1, in_w).repeat(in_w, 1).repeat(
int(bs*self.num_anchors/3), 1, 1).view(x.shape).type(FloatTensor)
grid_y = torch.linspace(0, in_h - 1, in_h).repeat(in_h, 1).t().repeat(
int(bs*self.num_anchors/3), 1, 1).view(y.shape).type(FloatTensor)
# 生成先验框的宽高
anchor_w = FloatTensor(scaled_anchors).index_select(1, LongTensor([0]))
anchor_h = FloatTensor(scaled_anchors).index_select(1, LongTensor([1]))
anchor_w = anchor_w.repeat(bs, 1).repeat(1, 1, in_h * in_w).view(w.shape)
anchor_h = anchor_h.repeat(bs, 1).repeat(1, 1, in_h * in_w).view(h.shape)
# 计算调整后的先验框中心与宽高
pred_boxes = FloatTensor(prediction[..., :4].shape)
pred_boxes[..., 0] = x + grid_x
pred_boxes[..., 1] = y + grid_y
pred_boxes[..., 2] = torch.exp(w) * anchor_w
pred_boxes[..., 3] = torch.exp(h) * anchor_h
for i in range(bs):
pred_boxes_for_ignore = pred_boxes[i]
pred_boxes_for_ignore = pred_boxes_for_ignore.view(-1, 4)
if len(target[i]) > 0:
gx = target[i][:, 0:1] * in_w
gy = target[i][:, 1:2] * in_h
gw = target[i][:, 2:3] * in_w
gh = target[i][:, 3:4] * in_h
gt_box = torch.FloatTensor(np.concatenate([gx, gy, gw, gh],-1)).type(FloatTensor)
anch_ious = iou(gt_box, pred_boxes_for_ignore)
for t in range(target[i].shape[0]):
anch_iou = anch_ious[t].view(pred_boxes[i].size()[:3])
noobj_mask[i][anch_iou>self.ignore_threshold] = 0
return noobj_mask, pred_boxes
