YOLOv4损失函数详细解释---------(供自己学习使用)

1.这部分代码,看了比较长时间。原因是以前一直不懂目标检测,感觉一学就废

2.文章思想部分借鉴了很多大佬

3.代码部分直接看的Bubbliiing佬

4.我只记录我看懂的部分,博客写的不好轻喷,欢迎指正

 

    def get_target(self, l, targets, anchors, in_h, in_w):
        #-----------------------------------------------------#
        #   计算一共有多少张图片,targets是归一化之后的坐标
        #-----------------------------------------------------#
        bs              = len(targets)
        #-----------------------------------------------------#
        #   用于选取哪些先验框不包含物体
        #-----------------------------------------------------#
        noobj_mask      = torch.ones(bs, len(self.anchors_mask[l]), in_h, in_w, requires_grad = False)
        #-----------------------------------------------------#
        #   让网络更加去关注小目标
        #-----------------------------------------------------#
        box_loss_scale  = torch.zeros(bs, len(self.anchors_mask[l]), in_h, in_w, requires_grad = False)
        #-----------------------------------------------------#
        #   batch_size, 3, 13, 13, 5 + num_classes
        #   zj-y_true就是将真实框的tensor变成这样
        #-----------------------------------------------------#
        y_true          = torch.zeros(bs, len(self.anchors_mask[l]), in_h, in_w, self.bbox_attrs, requires_grad = False)
        for b in range(bs):
            #zj-当前图片目标数为0就不用进行处理了
            if len(targets[b])==0:
                continue
            #构造batch_target,下面用来存储针对于当前预测特征层的真实值的状态
            batch_target = torch.zeros_like(targets[b])
            #-------------------------------------------------------#
            #   计算出正样本在特征层上的中心点
            #   zj---将正式框从归一化状态(targets的归一化是除以图片的宽和高得到的)调整为相对与当前预测特征层的状态
            #   zj---计算方式是x,y,w,h的状态
            #-------------------------------------------------------#
            batch_target[:, [0,2]] = targets[b][:, [0,2]] * in_w
            batch_target[:, [1,3]] = targets[b][:, [1,3]] * in_h
            batch_target[:, 4] = targets[b][:, 4]
            batch_target = batch_target.cpu()
            
            #-------------------------------------------------------#
            #   将真实框转换一个形式
            #   num_true_box, 4
            #-------------------------------------------------------#
            gt_box          = torch.FloatTensor(torch.cat((torch.zeros((batch_target.size(0), 2)), batch_target[:, 2:4]), 1))
            #-------------------------------------------------------#
            #   将先验框转换一个形式
            #   9, 4
            #-------------------------------------------------------#
            anchor_shapes   = torch.FloatTensor(torch.cat((torch.zeros((len(anchors), 2)), torch.FloatTensor(anchors)), 1))
            #-------------------------------------------------------#
            #   计算交并比
            #   self.calculate_iou(gt_box, anchor_shapes) = [num_true_box, 9]每一个真实框和9个先验框的重合情况
            #   best_ns:
            #   [每个真实框最大的重合度max_iou, 每一个真实框最重合的先验框的序号]
            #-------------------------------------------------------#
            best_ns = torch.argmax(self.calculate_iou(gt_box, anchor_shapes), dim=-1)

            for t, best_n in enumerate(best_ns):
                if best_n not in self.anchors_mask[l]:
                    continue
                #----------------------------------------#
                #   判断这个先验框是当前特征点的哪一个先验框
                #----------------------------------------#
                k = self.anchors_mask[l].index(best_n)
                #----------------------------------------#
                #   获得真实框属于哪个网格点
                #----------------------------------------#
                i = torch.floor(batch_target[t, 0]).long()
                j = torch.floor(batch_target[t, 1]).long()
                #----------------------------------------#
                #   取出真实框的种类
                #----------------------------------------#
                c = batch_target[t, 4].long()
                
                #----------------------------------------#
                #   zj-noobj_mask代表无目标的特征点,初始化全为1
                #----------------------------------------#
                noobj_mask[b, k, j, i] = 0
                #----------------------------------------#
                #   tx、ty代表中心调整参数的真实值
                #----------------------------------------#
                y_true[b, k, j, i, 0] = batch_target[t, 0]
                y_true[b, k, j, i, 1] = batch_target[t, 1]
                y_true[b, k, j, i, 2] = batch_target[t, 2]
                y_true[b, k, j, i, 3] = batch_target[t, 3]
                y_true[b, k, j, i, 4] = 1
                y_true[b, k, j, i, c + 5] = 1
                #----------------------------------------#
                #   用于获得xywh的比例
                #   大目标loss权重小,小目标loss权重大
                #----------------------------------------#
                box_loss_scale[b, k, j, i] = batch_target[t, 2] * batch_target[t, 3] / in_w / in_h
        return y_true, noobj_mask, box_loss_scale

上面这一部分,我感觉最核心的部分,是对真实值进行编码。真实值编码的结果就是将真实值编码成网络预测出的样子。

1.首先将归一化后的真实值targets,调整成相对于网络当前预测特征层的数值,并且存入到batch_target 这个tensor张量之中。

2.对目标物体真实值(相对于当前预测特征层)的宽高取出来,除此之外将使用k-means聚类得到的先验框的宽高取出来。(其实只需要取出相对于当前预测特征层的锚框宽高取出即可,但是b佬这里都取出来了)。将取出的真实框的宽高和锚框的宽高进行iou计算。得出iou值最大的那个锚框(也可以设定某一个阀值,只需要大于阀值也可)。

3.以1*3*13*13*25(batchsize,锚框种类,宽,长,参数(4个回归参数+置信度+20个类别概率)),接上面。如果第二个锚框和真实值的iou最大。y_true[1,1,真实框所在网格的宽,真实框所在网格的高,25)。将真实框的相对于预测特征层值填入y_true中。

 def get_ignore(self, l, x, y, h, w, targets, scaled_anchors, in_h, in_w, noobj_mask):
        #-----------------------------------------------------#
        #   计算一共有多少张图片
        #-----------------------------------------------------#
        bs = len(targets)

        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 = torch.linspace(0, in_w - 1, in_w).repeat(in_h, 1).repeat(
            int(bs * len(self.anchors_mask[l])), 1, 1).view(x.shape).type(FloatTensor)
        grid_y = torch.linspace(0, in_h - 1, in_h).repeat(in_w, 1).t().repeat(
            int(bs * len(self.anchors_mask[l])), 1, 1).view(y.shape).type(FloatTensor)

        # 生成先验框的宽高
        scaled_anchors_l = np.array(scaled_anchors)[self.anchors_mask[l]]
        anchor_w = FloatTensor(scaled_anchors_l).index_select(1, LongTensor([0]))
        anchor_h = FloatTensor(scaled_anchors_l).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_x    = torch.unsqueeze(x + grid_x, -1)
        pred_boxes_y    = torch.unsqueeze(y + grid_y, -1)
        pred_boxes_w    = torch.unsqueeze(torch.exp(w) * anchor_w, -1)
        pred_boxes_h    = torch.unsqueeze(torch.exp(h) * anchor_h, -1)
        pred_boxes      = torch.cat([pred_boxes_x, pred_boxes_y, pred_boxes_w, pred_boxes_h], dim = -1)
        for b in range(bs):           
            #-------------------------------------------------------#
            #   将预测结果转换一个形式
            #   pred_boxes_for_ignore      num_anchors, 4
            #-------------------------------------------------------#
            pred_boxes_for_ignore = pred_boxes[b].view(-1, 4)
            #-------------------------------------------------------#
            #   计算真实框,并把真实框转换成相对于特征层的大小
            #   gt_box      num_true_box, 4
            #-------------------------------------------------------#
            if len(targets[b]) > 0:
                batch_target = torch.zeros_like(targets[b])
                #-------------------------------------------------------#
                #   计算出正样本在特征层上的中心点
                #-------------------------------------------------------#
                batch_target[:, [0,2]] = targets[b][:, [0,2]] * in_w
                batch_target[:, [1,3]] = targets[b][:, [1,3]] * in_h
                batch_target = batch_target[:, :4]
                #-------------------------------------------------------#
                #   计算交并比
                #   anch_ious       num_true_box, num_anchors
                #-------------------------------------------------------#
                anch_ious = self.calculate_iou(batch_target, pred_boxes_for_ignore)
                #-------------------------------------------------------#
                #   每个先验框对应真实框的最大重合度
                #   anch_ious_max   num_anchors
                #-------------------------------------------------------#
                anch_ious_max, _    = torch.max(anch_ious, dim = 0)
                anch_ious_max       = anch_ious_max.view(pred_boxes[b].size()[:3])
                noobj_mask[b][anch_ious_max > self.ignore_threshold] = 0
        return noobj_mask, pred_boxes

 这一部分代码的核心思想就是筛选出正样本和负样本(其实正样本没啥好筛选的)

首先就是计算在1*3*13*13个网络中会产生多少个锚框,显然是507个。

将507个先验框的的x,y,w,h分别取出来与每个真实框的x,y,w,h进行iou计算。如果iou大于某个阀值就将noobj_mask里面对应位置置为0,代表该先验框既不是正样本,也不是负样本。

 def forward(self, l, input, targets=None):
        #----------------------------------------------------#
        #   l 代表使用的是第几个有效特征层
        #   input的shape为   bs, 3*(5+num_classes), 13, 13
        #                   bs, 3*(5+num_classes), 26, 26
        #                   bs, 3*(5+num_classes), 52, 52
        #   targets 真实框的标签情况 [batch_size, num_gt, 5]
        #----------------------------------------------------#
        #--------------------------------#
        #   获得图片数量,特征层的高和宽
        #--------------------------------#
        bs      = input.size(0)
        in_h    = input.size(2)
        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
        #   如果特征层为26x26的话,一个特征点就对应原来的图片上的16个像素点
        #   如果特征层为52x52的话,一个特征点就对应原来的图片上的8个像素点
        #   stride_h = stride_w = 32、16、8
        #-----------------------------------------------------------------------#
        stride_h = self.input_shape[0] / in_h
        stride_w = self.input_shape[1] / in_w
        #-------------------------------------------------#
        #   此时获得的scaled_anchors大小是相对于特征层的
        #-------------------------------------------------#
        scaled_anchors  = [(a_w / stride_w, a_h / stride_h) for a_w, a_h in self.anchors]
        #-----------------------------------------------#
        #   输入的input一共有三个,他们的shape分别是
        #   bs, 3 * (5+num_classes), 13, 13 => bs, 3, 5 + num_classes, 13, 13 => batch_size, 3, 13, 13, 5 + num_classes

        #   batch_size, 3, 13, 13, 5 + num_classes
        #   batch_size, 3, 26, 26, 5 + num_classes
        #   batch_size, 3, 52, 52, 5 + num_classes
        #-----------------------------------------------#
        prediction = input.view(bs, len(self.anchors_mask[l]), self.bbox_attrs, in_h, in_w).permute(0, 1, 3, 4, 2).contiguous()
        
        #-----------------------------------------------#
        #   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]
        h = prediction[..., 3]
        #-----------------------------------------------#
        #   获得置信度,是否有物体
        #-----------------------------------------------#
        conf = torch.sigmoid(prediction[..., 4])
        #-----------------------------------------------#
        #   种类置信度
        #-----------------------------------------------#
        pred_cls = torch.sigmoid(prediction[..., 5:])

        #-----------------------------------------------#
        #   获得网络应该有的预测结果
        #   noobj_mask代表无目标的特征点,无目标为0
        #-----------------------------------------------#
        y_true, noobj_mask, box_loss_scale = self.get_target(l, targets, scaled_anchors, in_h, in_w)

        #---------------------------------------------------------------#
        #   将预测结果进行解码,判断预测结果和真实值的重合程度
        #   如果重合程度过大则忽略,因为这些特征点属于预测比较准确的特征点
        #   作为负样本不合适
        #----------------------------------------------------------------#
        noobj_mask, pred_boxes = self.get_ignore(l, x, y, h, w, targets, scaled_anchors, in_h, in_w, noobj_mask)

        if self.cuda:
            y_true          = y_true.cuda()
            noobj_mask      = noobj_mask.cuda()
            box_loss_scale  = box_loss_scale.cuda()
        #-----------------------------------------------------------#
        #   reshape_y_true[...,2:3]和reshape_y_true[...,3:4]
        #   表示真实框的宽高,二者均在0-1之间
        #   真实框越大,比重越小,小框的比重更大。
        #-----------------------------------------------------------#
        box_loss_scale = 2 - box_loss_scale

        #---------------------------------------------------------------#
        #   计算预测结果和真实结果的CIOU
        #----------------------------------------------------------------#
        ciou        = (1 - self.box_ciou(pred_boxes[y_true[..., 4] == 1], y_true[..., :4][y_true[..., 4] == 1])) * box_loss_scale[y_true[..., 4] == 1]
        loss_loc    = torch.sum(ciou)
        #-----------------------------------------------------------#
        #   zj-计算置信度的loss=  正样本的置信度损失 + 负样本的置信度损失
        #-----------------------------------------------------------#
        loss_conf   = torch.sum(self.BCELoss(conf, y_true[..., 4]) * y_true[..., 4]) + \
                      torch.sum(self.BCELoss(conf, y_true[..., 4]) * noobj_mask)
        #   zj-这里根本没有做标签平滑(用来防止在训练集上过拟合的操作)
        loss_cls    = torch.sum(self.BCELoss(pred_cls[y_true[..., 4] == 1], self.smooth_labels(y_true[..., 5:][y_true[..., 4] == 1], self.label_smoothing, self.num_classes)))

        loss        = loss_loc + loss_conf + loss_cls
        #   zj-num_pos计算正样本的数量
        num_pos = torch.sum(y_true[..., 4])
        num_pos = torch.max(num_pos, torch.ones_like(num_pos))
        return loss, num_pos

这部分是损失函数的部分,

首先是x,y,w,h的回归损失,使用的是ciou损失。显然,只计算了正样本的回归损失。除此之外通过box_loss_scale来增加小样本的损失,减小大样本损失。最后torch.sum 得到损失值。从tensor取出真实值,进行计算。从tensor取出正样本值,进行计算。

其次是置信度损失,采用了Bceloss 。计算了正样本和负样本损失。这里noobj_mask的作用了,可以将计算的非正本和非负样本对应位置的损失进行置0。最后torch.sum 得到损失值。

未从tensor中取出,根据真实值编码在对应位置进行计算。

最后是分类损失,分类损失采用了Bceloss。计算了正样本损失。从tensor取出真实值,进行计算。从tensor取出正样本值,进行计算。同时使用了标签平滑,防止训练过程过拟合。标签平滑的意思比如真实值编码为[1,0,0],现在将真实值变为[0.95,0.025,0.025]其实就是对训练过程进行惩罚。

 

import torch
import torch.nn as nn
import math
import numpy as np

class YOLOLoss(nn.Module):
    def __init__(self, anchors, num_classes, input_shape, cuda, anchors_mask = [[6,7,8], [3,4,5], [0,1,2]], label_smoothing = 0):
        super(YOLOLoss, self).__init__()
        #-----------------------------------------------------------#
        #   13x13的特征层对应的anchor是[142, 110],[192, 243],[459, 401]
        #   26x26的特征层对应的anchor是[36, 75],[76, 55],[72, 146]
        #   52x52的特征层对应的anchor是[12, 16],[19, 36],[40, 28]
        #-----------------------------------------------------------#
        self.anchors        = anchors
        self.num_classes    = num_classes
        self.bbox_attrs     = 5 + num_classes
        self.input_shape    = input_shape
        self.anchors_mask   = anchors_mask
        self.label_smoothing = label_smoothing

        self.ignore_threshold = 0.5
        self.cuda = cuda

    def clip_by_tensor(self, 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(self, pred, target):
        return torch.pow(pred - target, 2)

    def BCELoss(self, pred, target):
        epsilon = 1e-7
        pred    = self.clip_by_tensor(pred, epsilon, 1.0 - epsilon)
        output  = - target * torch.log(pred) - (1.0 - target) * torch.log(1.0 - pred)
        return output

    def box_ciou(self, 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
        #   zj-首先计算两个矩形的外包边
        #----------------------------------------------------#
        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为相交矩形的面积
        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

    #---------------------------------------------------#
    #   平滑标签
    #---------------------------------------------------#
    def smooth_labels(self, y_true, label_smoothing, num_classes):
        return y_true * (1.0 - label_smoothing) + label_smoothing / num_classes

    def forward(self, l, input, targets=None):
        #----------------------------------------------------#
        #   l 代表使用的是第几个有效特征层
        #   input的shape为   bs, 3*(5+num_classes), 13, 13
        #                   bs, 3*(5+num_classes), 26, 26
        #                   bs, 3*(5+num_classes), 52, 52
        #   targets 真实框的标签情况 [batch_size, num_gt, 5]
        #----------------------------------------------------#
        #--------------------------------#
        #   获得图片数量,特征层的高和宽
        #--------------------------------#
        bs      = input.size(0)
        in_h    = input.size(2)
        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
        #   如果特征层为26x26的话,一个特征点就对应原来的图片上的16个像素点
        #   如果特征层为52x52的话,一个特征点就对应原来的图片上的8个像素点
        #   stride_h = stride_w = 32、16、8
        #-----------------------------------------------------------------------#
        stride_h = self.input_shape[0] / in_h
        stride_w = self.input_shape[1] / in_w
        #-------------------------------------------------#
        #   此时获得的scaled_anchors大小是相对于特征层的
        #-------------------------------------------------#
        scaled_anchors  = [(a_w / stride_w, a_h / stride_h) for a_w, a_h in self.anchors]
        #-----------------------------------------------#
        #   输入的input一共有三个,他们的shape分别是
        #   bs, 3 * (5+num_classes), 13, 13 => bs, 3, 5 + num_classes, 13, 13 => batch_size, 3, 13, 13, 5 + num_classes

        #   batch_size, 3, 13, 13, 5 + num_classes
        #   batch_size, 3, 26, 26, 5 + num_classes
        #   batch_size, 3, 52, 52, 5 + num_classes
        #-----------------------------------------------#
        prediction = input.view(bs, len(self.anchors_mask[l]), self.bbox_attrs, in_h, in_w).permute(0, 1, 3, 4, 2).contiguous()
        
        #-----------------------------------------------#
        #   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]
        h = prediction[..., 3]
        #-----------------------------------------------#
        #   获得置信度,是否有物体
        #-----------------------------------------------#
        conf = torch.sigmoid(prediction[..., 4])
        #-----------------------------------------------#
        #   种类置信度
        #-----------------------------------------------#
        pred_cls = torch.sigmoid(prediction[..., 5:])

        #-----------------------------------------------#
        #   获得网络应该有的预测结果
        #   noobj_mask代表无目标的特征点,无目标为0
        #-----------------------------------------------#
        y_true, noobj_mask, box_loss_scale = self.get_target(l, targets, scaled_anchors, in_h, in_w)

        #---------------------------------------------------------------#
        #   将预测结果进行解码,判断预测结果和真实值的重合程度
        #   如果重合程度过大则忽略,因为这些特征点属于预测比较准确的特征点
        #   作为负样本不合适
        #----------------------------------------------------------------#
        noobj_mask, pred_boxes = self.get_ignore(l, x, y, h, w, targets, scaled_anchors, in_h, in_w, noobj_mask)

        if self.cuda:
            y_true          = y_true.cuda()
            noobj_mask      = noobj_mask.cuda()
            box_loss_scale  = box_loss_scale.cuda()
        #-----------------------------------------------------------#
        #   reshape_y_true[...,2:3]和reshape_y_true[...,3:4]
        #   表示真实框的宽高,二者均在0-1之间
        #   真实框越大,比重越小,小框的比重更大。
        #-----------------------------------------------------------#
        box_loss_scale = 2 - box_loss_scale

        #---------------------------------------------------------------#
        #   计算预测结果和真实结果的CIOU
        #----------------------------------------------------------------#
        ciou        = (1 - self.box_ciou(pred_boxes[y_true[..., 4] == 1], y_true[..., :4][y_true[..., 4] == 1])) * box_loss_scale[y_true[..., 4] == 1]
        loss_loc    = torch.sum(ciou)
        #-----------------------------------------------------------#
        #   zj-计算置信度的loss=  正样本的置信度损失 + 负样本的置信度损失
        #-----------------------------------------------------------#
        loss_conf   = torch.sum(self.BCELoss(conf, y_true[..., 4]) * y_true[..., 4]) + \
                      torch.sum(self.BCELoss(conf, y_true[..., 4]) * noobj_mask)
        #   zj-这里根本没有做标签平滑(用来防止在训练集上过拟合的操作)
        loss_cls    = torch.sum(self.BCELoss(pred_cls[y_true[..., 4] == 1], self.smooth_labels(y_true[..., 5:][y_true[..., 4] == 1], self.label_smoothing, self.num_classes)))

        loss        = loss_loc + loss_conf + loss_cls
        #   zj-num_pos计算正样本的数量
        num_pos = torch.sum(y_true[..., 4])
        num_pos = torch.max(num_pos, torch.ones_like(num_pos))
        return loss, num_pos

    def calculate_iou(self, _box_a, _box_b):
        #-----------------------------------------------------------#
        #   计算真实框的左上角和右下角
        #-----------------------------------------------------------#
        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
        #-----------------------------------------------------------#
        #   计算先验框获得的预测框的左上角和右下角
        #-----------------------------------------------------------#
        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

        #-----------------------------------------------------------#
        #   将真实框和预测框都转化成左上角右下角的形式
        #-----------------------------------------------------------#
        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为真实框的数量,B为先验框的数量
        #-----------------------------------------------------------#
        A = box_a.size(0)
        B = box_b.size(0)

        #-----------------------------------------------------------#
        #   计算交的面积
        #-----------------------------------------------------------#
        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))
        #   zj--torch.clamp()输入一个张量,使张量里面的类容都不小于最小值或者大于最大值
        inter   = torch.clamp((max_xy - min_xy), min=0)
        inter   = inter[:, :, 0] * inter[:, :, 1]
        #-----------------------------------------------------------#
        #   计算预测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]
    
    def get_target(self, l, targets, anchors, in_h, in_w):
        #-----------------------------------------------------#
        #   计算一共有多少张图片,targets是归一化之后的坐标
        #-----------------------------------------------------#
        bs              = len(targets)
        #-----------------------------------------------------#
        #   用于选取哪些先验框不包含物体
        #-----------------------------------------------------#
        noobj_mask      = torch.ones(bs, len(self.anchors_mask[l]), in_h, in_w, requires_grad = False)
        #-----------------------------------------------------#
        #   让网络更加去关注小目标
        #-----------------------------------------------------#
        box_loss_scale  = torch.zeros(bs, len(self.anchors_mask[l]), in_h, in_w, requires_grad = False)
        #-----------------------------------------------------#
        #   batch_size, 3, 13, 13, 5 + num_classes
        #   zj-y_true就是将真实框的tensor变成这样
        #-----------------------------------------------------#
        y_true          = torch.zeros(bs, len(self.anchors_mask[l]), in_h, in_w, self.bbox_attrs, requires_grad = False)
        for b in range(bs):
            #zj-当前图片目标数为0就不用进行处理了
            if len(targets[b])==0:
                continue
            #构造batch_target,下面用来存储针对于当前预测特征层的真实值的状态
            batch_target = torch.zeros_like(targets[b])
            #-------------------------------------------------------#
            #   计算出正样本在特征层上的中心点
            #   zj---将正式框从归一化状态(targets的归一化是除以图片的宽和高得到的)调整为相对与当前预测特征层的状态
            #   zj---计算方式是x,y,w,h的状态
            #-------------------------------------------------------#
            batch_target[:, [0,2]] = targets[b][:, [0,2]] * in_w
            batch_target[:, [1,3]] = targets[b][:, [1,3]] * in_h
            batch_target[:, 4] = targets[b][:, 4]
            batch_target = batch_target.cpu()
            
            #-------------------------------------------------------#
            #   将真实框转换一个形式
            #   num_true_box, 4
            #-------------------------------------------------------#
            gt_box          = torch.FloatTensor(torch.cat((torch.zeros((batch_target.size(0), 2)), batch_target[:, 2:4]), 1))
            #-------------------------------------------------------#
            #   将先验框转换一个形式
            #   9, 4
            #-------------------------------------------------------#
            anchor_shapes   = torch.FloatTensor(torch.cat((torch.zeros((len(anchors), 2)), torch.FloatTensor(anchors)), 1))
            #-------------------------------------------------------#
            #   计算交并比
            #   self.calculate_iou(gt_box, anchor_shapes) = [num_true_box, 9]每一个真实框和9个先验框的重合情况
            #   best_ns:
            #   [每个真实框最大的重合度max_iou, 每一个真实框最重合的先验框的序号]
            #-------------------------------------------------------#
            best_ns = torch.argmax(self.calculate_iou(gt_box, anchor_shapes), dim=-1)

            for t, best_n in enumerate(best_ns):
                if best_n not in self.anchors_mask[l]:
                    continue
                #----------------------------------------#
                #   判断这个先验框是当前特征点的哪一个先验框
                #----------------------------------------#
                k = self.anchors_mask[l].index(best_n)
                #----------------------------------------#
                #   获得真实框属于哪个网格点
                #----------------------------------------#
                i = torch.floor(batch_target[t, 0]).long()
                j = torch.floor(batch_target[t, 1]).long()
                #----------------------------------------#
                #   取出真实框的种类
                #----------------------------------------#
                c = batch_target[t, 4].long()
                
                #----------------------------------------#
                #   zj-noobj_mask代表无目标的特征点,初始化全为1
                #----------------------------------------#
                noobj_mask[b, k, j, i] = 0
                #----------------------------------------#
                #   tx、ty代表中心调整参数的真实值
                #----------------------------------------#
                y_true[b, k, j, i, 0] = batch_target[t, 0]
                y_true[b, k, j, i, 1] = batch_target[t, 1]
                y_true[b, k, j, i, 2] = batch_target[t, 2]
                y_true[b, k, j, i, 3] = batch_target[t, 3]
                y_true[b, k, j, i, 4] = 1
                y_true[b, k, j, i, c + 5] = 1
                #----------------------------------------#
                #   用于获得xywh的比例
                #   大目标loss权重小,小目标loss权重大
                #----------------------------------------#
                box_loss_scale[b, k, j, i] = batch_target[t, 2] * batch_target[t, 3] / in_w / in_h
        return y_true, noobj_mask, box_loss_scale

    def get_ignore(self, l, x, y, h, w, targets, scaled_anchors, in_h, in_w, noobj_mask):
        #-----------------------------------------------------#
        #   计算一共有多少张图片
        #-----------------------------------------------------#
        bs = len(targets)

        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 = torch.linspace(0, in_w - 1, in_w).repeat(in_h, 1).repeat(
            int(bs * len(self.anchors_mask[l])), 1, 1).view(x.shape).type(FloatTensor)
        grid_y = torch.linspace(0, in_h - 1, in_h).repeat(in_w, 1).t().repeat(
            int(bs * len(self.anchors_mask[l])), 1, 1).view(y.shape).type(FloatTensor)

        # 生成先验框的宽高
        scaled_anchors_l = np.array(scaled_anchors)[self.anchors_mask[l]]
        anchor_w = FloatTensor(scaled_anchors_l).index_select(1, LongTensor([0]))
        anchor_h = FloatTensor(scaled_anchors_l).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_x    = torch.unsqueeze(x + grid_x, -1)
        pred_boxes_y    = torch.unsqueeze(y + grid_y, -1)
        pred_boxes_w    = torch.unsqueeze(torch.exp(w) * anchor_w, -1)
        pred_boxes_h    = torch.unsqueeze(torch.exp(h) * anchor_h, -1)
        pred_boxes      = torch.cat([pred_boxes_x, pred_boxes_y, pred_boxes_w, pred_boxes_h], dim = -1)
        for b in range(bs):           
            #-------------------------------------------------------#
            #   将预测结果转换一个形式
            #   pred_boxes_for_ignore      num_anchors, 4
            #-------------------------------------------------------#
            pred_boxes_for_ignore = pred_boxes[b].view(-1, 4)
            #-------------------------------------------------------#
            #   计算真实框,并把真实框转换成相对于特征层的大小
            #   gt_box      num_true_box, 4
            #-------------------------------------------------------#
            if len(targets[b]) > 0:
                batch_target = torch.zeros_like(targets[b])
                #-------------------------------------------------------#
                #   计算出正样本在特征层上的中心点
                #-------------------------------------------------------#
                batch_target[:, [0,2]] = targets[b][:, [0,2]] * in_w
                batch_target[:, [1,3]] = targets[b][:, [1,3]] * in_h
                batch_target = batch_target[:, :4]
                #-------------------------------------------------------#
                #   计算交并比
                #   anch_ious       num_true_box, num_anchors
                #-------------------------------------------------------#
                anch_ious = self.calculate_iou(batch_target, pred_boxes_for_ignore)
                #-------------------------------------------------------#
                #   每个先验框对应真实框的最大重合度
                #   anch_ious_max   num_anchors
                #-------------------------------------------------------#
                anch_ious_max, _    = torch.max(anch_ious, dim = 0)
                anch_ious_max       = anch_ious_max.view(pred_boxes[b].size()[:3])
                noobj_mask[b][anch_ious_max > self.ignore_threshold] = 0
        return noobj_mask, pred_boxes

def weights_init(net, init_type='normal', init_gain = 0.02):
    def init_func(m):
        classname = m.__class__.__name__
        if hasattr(m, 'weight') and classname.find('Conv') != -1:
            if init_type == 'normal':
                torch.nn.init.normal_(m.weight.data, 0.0, init_gain)
            elif init_type == 'xavier':
                torch.nn.init.xavier_normal_(m.weight.data, gain=init_gain)
            elif init_type == 'kaiming':
                torch.nn.init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')
            elif init_type == 'orthogonal':
                torch.nn.init.orthogonal_(m.weight.data, gain=init_gain)
            else:
                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
        elif classname.find('BatchNorm2d') != -1:
            torch.nn.init.normal_(m.weight.data, 1.0, 0.02)
            torch.nn.init.constant_(m.bias.data, 0.0)
    print('initialize network with %s type' % init_type)
    net.apply(init_func)

完整代码如上

你可能感兴趣的:(pytorch,目标检测)