【项目实践】YOLO V4万字原理详细讲解并训练自己的数据集(pytorch完整项目打包下载)

2020-06-22 18:44:48 浏览数 (1)

1、什么是YOLOV4

YOLOV4是YOLOV3的改进版,在YOLOV3的基础上结合了非常多的小Tricks。尽管没有目标检测上革命性的改变,但是YOLOV4依然很好的结合了速度与精度。

根据上图也可以看出来,YOLOV4在YOLOV3的基础上,在FPS不下降的情况下,mAP达到了44,提高非常明显。

YOLOV4整体上的检测思路和YOLOV3相比相差并不大,都是使用三个特征层进行分类与回归预测。

YOLOV4改进的部分(不完全)

1、主干特征提取网络:DarkNet53 => CSPDarkNet53

2、特征金字塔:SPP,PAN

3、分类回归层:YOLOv3(未改变)

4、训练用到的小技巧:Mosaic数据增强、Label Smoothing平滑、CIOU、学习率余弦退火衰减

5、激活函数:使用Mish激活函数

以上并非全部的改进部分,还存在一些其它的改进,由于YOLOV4使用的改进实在太多了,很难完全实现与列出来,这里只列出来了一些我比较感兴趣,而且非常有效的改进。

2、YOLOV4结构解析

2.1、主干特征提取网络Backbone

当输入是416x416时,特征结构如下:

当输入是608x608时,特征结构如下:

主干特征提取网络Backbone的改进点有两个:

a).主干特征提取网络:DarkNet53 => CSPDarkNet53;

b).激活函数:使用Mish激活函数;

如果大家对YOLOV3比较熟悉的话,应该知道Darknet53的结构,其由一系列残差网络结构构成。在Darknet53中,其存在resblock_body模块,其由一次下采样和多次残差结构的堆叠构成,Darknet53便是由resblock_body模块组合而成。

而在YOLOV4中,其对该部分进行了一定的修改。

1、其一是将DarknetConv2D的激活函数由LeakyReLU修改成了Mish,卷积块由DarknetConv2D_BN_Leaky变成了DarknetConv2D_BN_Mish。

Mish函数的公式与图像如下:

2、其二是将resblock_body的结构进行修改,使用了CSPnet结构。此时YOLOV4当中的Darknet53被修改成了CSPDarknet53。

CSPnet结构并不算复杂,就是将原来的残差块的堆叠进行了一个拆分,拆成左右两部分: 主干部分继续进行原来的残差块的堆叠; 另一部分则像一个残差边一样,经过少量处理直接连接到最后。 因此可以认为CSP中存在一个大的残差边。

代码语言:javascript复制
#---------------------------------------------------#
#   CSPdarknet的结构块
#   存在一个大残差边
#   这个大残差边绕过了很多的残差结构
#---------------------------------------------------#
class Resblock_body(nn.Module):
    def __init__(self, in_channels, out_channels, num_blocks, first):
        super(Resblock_body, self).__init__()

        self.downsample_conv = BasicConv(in_channels, out_channels, 3, stride=2)

        if first:
            self.split_conv0 = BasicConv(out_channels, out_channels, 1)
            self.split_conv1 = BasicConv(out_channels, out_channels, 1)  
            self.blocks_conv = nn.Sequential(
                Resblock(channels=out_channels, hidden_channels=out_channels//2),
                BasicConv(out_channels, out_channels, 1)
            )
            self.concat_conv = BasicConv(out_channels*2, out_channels, 1)
        else:
            self.split_conv0 = BasicConv(out_channels, out_channels//2, 1)
            self.split_conv1 = BasicConv(out_channels, out_channels//2, 1)

            self.blocks_conv = nn.Sequential(
                *[Resblock(out_channels//2) for _ in range(num_blocks)],
                BasicConv(out_channels//2, out_channels//2, 1)
            )
            self.concat_conv = BasicConv(out_channels, out_channels, 1)

    def forward(self, x):
        x = self.downsample_conv(x)

        x0 = self.split_conv0(x)

        x1 = self.split_conv1(x)
        x1 = self.blocks_conv(x1)

        x = torch.cat([x1, x0], dim=1)
        x = self.concat_conv(x)

        return x

全部实现代码为:

代码语言:javascript复制
import torch
import torch.nn.functional as F
import torch.nn as nn
import math
from collections import OrderedDict

#-------------------------------------------------#
#   MISH激活函数
#-------------------------------------------------#
class Mish(nn.Module):
    def __init__(self):
        super(Mish, self).__init__()

    def forward(self, x):
        return x * torch.tanh(F.softplus(x))

#-------------------------------------------------#
#   卷积块
#   CONV BATCHNORM MISH
#-------------------------------------------------#
class BasicConv(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1):
        super(BasicConv, self).__init__()

        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, kernel_size//2, bias=False)
        self.bn = nn.BatchNorm2d(out_channels)
        self.activation = Mish()

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        x = self.activation(x)
        return x

#---------------------------------------------------#
#   CSPdarknet的结构块的组成部分
#   内部堆叠的残差块
#---------------------------------------------------#
class Resblock(nn.Module):
    def __init__(self, channels, hidden_channels=None, residual_activation=nn.Identity()):
        super(Resblock, self).__init__()

        if hidden_channels is None:
            hidden_channels = channels

        self.block = nn.Sequential(
            BasicConv(channels, hidden_channels, 1),
            BasicConv(hidden_channels, channels, 3)
        )

    def forward(self, x):
        return x self.block(x)

#---------------------------------------------------#
#   CSPdarknet的结构块
#   存在一个大残差边
#   这个大残差边绕过了很多的残差结构
#---------------------------------------------------#
class Resblock_body(nn.Module):
    def __init__(self, in_channels, out_channels, num_blocks, first):
        super(Resblock_body, self).__init__()

        self.downsample_conv = BasicConv(in_channels, out_channels, 3, stride=2)

        if first:
            self.split_conv0 = BasicConv(out_channels, out_channels, 1)
            self.split_conv1 = BasicConv(out_channels, out_channels, 1)  
            self.blocks_conv = nn.Sequential(
                Resblock(channels=out_channels, hidden_channels=out_channels//2),
                BasicConv(out_channels, out_channels, 1)
            )
            self.concat_conv = BasicConv(out_channels*2, out_channels, 1)
        else:
            self.split_conv0 = BasicConv(out_channels, out_channels//2, 1)
            self.split_conv1 = BasicConv(out_channels, out_channels//2, 1)

            self.blocks_conv = nn.Sequential(
                *[Resblock(out_channels//2) for _ in range(num_blocks)],
                BasicConv(out_channels//2, out_channels//2, 1)
            )
            self.concat_conv = BasicConv(out_channels, out_channels, 1)

    def forward(self, x):
        x = self.downsample_conv(x)

        x0 = self.split_conv0(x)

        x1 = self.split_conv1(x)
        x1 = self.blocks_conv(x1)

        x = torch.cat([x1, x0], dim=1)
        x = self.concat_conv(x)

        return x

class CSPDarkNet(nn.Module):
    def __init__(self, layers):
        super(CSPDarkNet, self).__init__()
        self.inplanes = 32
        self.conv1 = BasicConv(3, self.inplanes, kernel_size=3, stride=1)
        self.feature_channels = [64, 128, 256, 512, 1024]

        self.stages = nn.ModuleList([
            Resblock_body(self.inplanes, self.feature_channels[0], layers[0], first=True),
            Resblock_body(self.feature_channels[0], self.feature_channels[1], layers[1], first=False),
            Resblock_body(self.feature_channels[1], self.feature_channels[2], layers[2], first=False),
            Resblock_body(self.feature_channels[2], self.feature_channels[3], layers[3], first=False),
            Resblock_body(self.feature_channels[3], self.feature_channels[4], layers[4], first=False)
        ])

        self.num_features = 1
        # 进行权值初始化
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()


    def forward(self, x):
        x = self.conv1(x)

        x = self.stages[0](x)
        x = self.stages[1](x)
        out3 = self.stages[2](x)
        out4 = self.stages[3](out3)
        out5 = self.stages[4](out4)

        return out3, out4, out5

def darknet53(pretrained, **kwargs):
    model = CSPDarkNet([1, 2, 8, 8, 4])
    if pretrained:
        if isinstance(pretrained, str):
            model.load_state_dict(torch.load(pretrained))
        else:
            raise Exception("darknet request a pretrained path. got [{}]".format(pretrained))
    return model

3、特征金字塔

当输入是416x416时,特征结构如下:

当输入是608x608时,特征结构如下:

在特征金字塔部分,YOLOV4结合了两种改进:

a).使用了SPP结构。

b).使用了PANet结构。

如上图所示,除去CSPDarknet53和Yolo Head的结构外,都是特征金字塔的结构。

1、SPP结构参杂在对CSPdarknet53的最后一个特征层的卷积里,在对CSPdarknet53的最后一个特征层进行三次DarknetConv2D_BN_Leaky卷积后,分别利用四个不同尺度的最大池化进行处理,最大池化的池化核大小分别为13x13、9x9、5x5、1x1(1x1即无处理)

代码语言:javascript复制
#---------------------------------------------------#
#   SPP结构,利用不同大小的池化核进行池化
#   池化后堆叠
#---------------------------------------------------#
class SpatialPyramidPooling(nn.Module):
    def __init__(self, pool_sizes=[5, 9, 13]):
        super(SpatialPyramidPooling, self).__init__()

        self.maxpools = nn.ModuleList([nn.MaxPool2d(pool_size, 1, pool_size//2) for pool_size in pool_sizes])

    def forward(self, x):
        features = [maxpool(x) for maxpool in self.maxpools[::-1]]
        features = torch.cat(features   [x], dim=1)

        return features

其可以它能够极大地增加感受野,分离出最显著的上下文特征。

2、PANet是2018的一种实例分割算法,其具体结构由反复提升特征的意思。

上图为原始的PANet的结构,可以看出来其具有一个非常重要的特点就是特征的反复提取。 在(a)里面是传统的特征金字塔结构,在完成特征金字塔从下到上的特征提取后,还需要实现(b)中从上到下的特征提取。

而在YOLOV4当中,其主要是在三个有效特征层上使用了PANet结构。

实现代码如下:

代码语言:javascript复制
#---------------------------------------------------#
#   yolo_body
#---------------------------------------------------#
class YoloBody(nn.Module):
    def __init__(self, config):
        super(YoloBody, self).__init__()
        self.config = config
        #  backbone
        self.backbone = darknet53(None)

        self.conv1 = make_three_conv([512,1024],1024)
        self.SPP = SpatialPyramidPooling()
        self.conv2 = make_three_conv([512,1024],2048)

        self.upsample1 = Upsample(512,256)
        self.conv_for_P4 = conv2d(512,256,1)
        self.make_five_conv1 = make_five_conv([256, 512],512)

        self.upsample2 = Upsample(256,128)
        self.conv_for_P3 = conv2d(256,128,1)
        self.make_five_conv2 = make_five_conv([128, 256],256)
        # 3*(5 num_classes)=3*(5 20)=3*(4 1 20)=75
        final_out_filter2 = len(config["yolo"]["anchors"][2]) * (5   config["yolo"]["classes"])
        self.yolo_head3 = yolo_head([256, final_out_filter2],128)

        self.down_sample1 = conv2d(128,256,3,stride=2)
        self.make_five_conv3 = make_five_conv([256, 512],512)
        # 3*(5 num_classes)=3*(5 20)=3*(4 1 20)=75
        final_out_filter1 = len(config["yolo"]["anchors"][1]) * (5   config["yolo"]["classes"])
        self.yolo_head2 = yolo_head([512, final_out_filter1],256)


        self.down_sample2 = conv2d(256,512,3,stride=2)
        self.make_five_conv4 = make_five_conv([512, 1024],1024)
        # 3*(5 num_classes)=3*(5 20)=3*(4 1 20)=75
        final_out_filter0 = len(config["yolo"]["anchors"][0]) * (5   config["yolo"]["classes"])
        self.yolo_head1 = yolo_head([1024, final_out_filter0],512)


    def forward(self, x):
        #  backbone
        x2, x1, x0 = self.backbone(x)

        P5 = self.conv1(x0)
        P5 = self.SPP(P5)
        P5 = self.conv2(P5)

        P5_upsample = self.upsample1(P5)
        P4 = self.conv_for_P4(x1)
        P4 = torch.cat([P4,P5_upsample],axis=1)
        P4 = self.make_five_conv1(P4)

        P4_upsample = self.upsample2(P4)
        P3 = self.conv_for_P3(x2)
        P3 = torch.cat([P3,P4_upsample],axis=1)
        P3 = self.make_five_conv2(P3)

        P3_downsample = self.down_sample1(P3)
        P4 = torch.cat([P3_downsample,P4],axis=1)
        P4 = self.make_five_conv3(P4)

        P4_downsample = self.down_sample2(P4)
        P5 = torch.cat([P4_downsample,P5],axis=1)
        P5 = self.make_five_conv4(P5)

        out2 = self.yolo_head3(P3)
        out1 = self.yolo_head2(P4)
        out0 = self.yolo_head1(P5)

        return out0, out1, out2

4、YoloHead利用获得到的特征进行预测

当输入是416x416时,特征结构如下:

当输入是608x608时,特征结构如下:

1、在特征利用部分,YoloV4提取多特征层进行目标检测,一共提取三个特征层,分别位于中间层,中下层,底层,三个特征层的shape分别为(76,76,256)、(38,38,512)、(19,19,1024)。

2、输出层的shape分别为(19,19,75),(38,38,75),(76,76,75),最后一个维度为75是因为该图是基于voc数据集的,它的类为20种,YoloV4只有针对每一个特征层存在3个先验框,所以最后维度为3x25;

如果使用的是coco训练集,类则为80种,最后的维度应该为255 = 3x85,三个特征层的shape为(19,19,255),(38,38,255),(76,76,255)

代码语言:javascript复制
#---------------------------------------------------#
#   最后获得yolov4的输出
#---------------------------------------------------#
def yolo_head(filters_list, in_filters):
    m = nn.Sequential(
        conv2d(in_filters, filters_list[0], 3),
        nn.Conv2d(filters_list[0], filters_list[1], 1),
    )
    return m

#---------------------------------------------------#
#   yolo_body
#---------------------------------------------------#
class YoloBody(nn.Module):
    def __init__(self, config):
        super(YoloBody, self).__init__()
        self.config = config
        #  backbone
        self.backbone = darknet53(None)

        self.conv1 = make_three_conv([512,1024],1024)
        self.SPP = SpatialPyramidPooling()
        self.conv2 = make_three_conv([512,1024],2048)

        self.upsample1 = Upsample(512,256)
        self.conv_for_P4 = conv2d(512,256,1)
        self.make_five_conv1 = make_five_conv([256, 512],512)

        self.upsample2 = Upsample(256,128)
        self.conv_for_P3 = conv2d(256,128,1)
        self.make_five_conv2 = make_five_conv([128, 256],256)
        # 3*(5 num_classes)=3*(5 20)=3*(4 1 20)=75
        final_out_filter2 = len(config["yolo"]["anchors"][2]) * (5   config["yolo"]["classes"])
        self.yolo_head3 = yolo_head([256, final_out_filter2],128)

        self.down_sample1 = conv2d(128,256,3,stride=2)
        self.make_five_conv3 = make_five_conv([256, 512],512)
        # 3*(5 num_classes)=3*(5 20)=3*(4 1 20)=75
        final_out_filter1 = len(config["yolo"]["anchors"][1]) * (5   config["yolo"]["classes"])
        self.yolo_head2 = yolo_head([512, final_out_filter1],256)


        self.down_sample2 = conv2d(256,512,3,stride=2)
        self.make_five_conv4 = make_five_conv([512, 1024],1024)
        # 3*(5 num_classes)=3*(5 20)=3*(4 1 20)=75
        final_out_filter0 = len(config["yolo"]["anchors"][0]) * (5   config["yolo"]["classes"])
        self.yolo_head1 = yolo_head([1024, final_out_filter0],512)


    def forward(self, x):
        #  backbone
        x2, x1, x0 = self.backbone(x)

        P5 = self.conv1(x0)
        P5 = self.SPP(P5)
        P5 = self.conv2(P5)

        P5_upsample = self.upsample1(P5)
        P4 = self.conv_for_P4(x1)
        P4 = torch.cat([P4,P5_upsample],axis=1)
        P4 = self.make_five_conv1(P4)

        P4_upsample = self.upsample2(P4)
        P3 = self.conv_for_P3(x2)
        P3 = torch.cat([P3,P4_upsample],axis=1)
        P3 = self.make_five_conv2(P3)

        P3_downsample = self.down_sample1(P3)
        P4 = torch.cat([P3_downsample,P4],axis=1)
        P4 = self.make_five_conv3(P4)

        P4_downsample = self.down_sample2(P4)
        P5 = torch.cat([P4_downsample,P5],axis=1)
        P5 = self.make_five_conv4(P5)

        out2 = self.yolo_head3(P3)
        out1 = self.yolo_head2(P4)
        out0 = self.yolo_head1(P5)

        return out0, out1, out2

5、预测结果的解码

由第二步我们可以获得三个特征层的预测结果,shape分别为(N,19,19,255),(N,38,38,255),(N,76,76,255)的数据,对应每个图分为19x19、38x38、76x76的网格上3个预测框的位置。

但是这个预测结果并不对应着最终的预测框在图片上的位置,还需要解码才可以完成。

此处要讲一下yolo3的预测原理,yolo3的3个特征层分别将整幅图分为19x19、38x38、76x76的网格,每个网络点负责一个区域的检测。

我们知道特征层的预测结果对应着三个预测框的位置,我们先将其reshape一下,其结果为(N,19,19,3,85),(N,38,38,3,85),(N,76,76,3,85)。

最后一个维度中的85包含了4 1 80,分别代表x_offset、y_offset、h和w、置信度、分类结果。

yolo3的解码过程就是将每个网格点加上它对应的x_offset和y_offset,加完后的结果就是预测框的中心,然后再利用 先验框和h、w结合 计算出预测框的长和宽。这样就能得到整个预测框的位置了。

当然得到最终的预测结构后还要进行得分排序与非极大抑制筛选;

这一部分基本上是所有目标检测通用的部分。不过该项目的处理方式与其它项目不同。其对于每一个类进行判别。

1、取出每一类得分大于self.obj_threshold的框和得分。

2、利用框的位置和得分进行非极大抑制。

实现代码如下,当调用yolo_eval时,就会对每个特征层进行解码:

代码语言:javascript复制
class DecodeBox(nn.Module):
    def __init__(self, anchors, num_classes, img_size):
        super(DecodeBox, 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

    def forward(self, input):
        # input为bs,3*(1 4 num_classes),13,13

        # 一共多少张图片
        batch_size = input.size(0)
        # 13,13
        input_height = input.size(2)
        input_width = 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
        # 416/13 = 32
        stride_h = self.img_size[1] / input_height
        stride_w = self.img_size[0] / input_width

        # 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 = [(anchor_width / stride_w, anchor_height / stride_h) for anchor_width, anchor_height in self.anchors]

        # bs,3*(5 num_classes),13,13 -> bs,3,13,13,(5 num_classes)
        prediction = input.view(batch_size, self.num_anchors,
                                self.bbox_attrs, input_height, input_width).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]  # Width
        h = prediction[..., 3]  # Height

        # 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:])  # Cls pred.

        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 batch_size,3,13,13
        grid_x = torch.linspace(0, input_width - 1, input_width).repeat(input_width, 1).repeat(
            batch_size * self.num_anchors, 1, 1).view(x.shape).type(FloatTensor)
        grid_y = torch.linspace(0, input_height - 1, input_height).repeat(input_height, 1).t().repeat(
            batch_size * self.num_anchors, 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(batch_size, 1).repeat(1, 1, input_height * input_width).view(w.shape)
        anchor_h = anchor_h.repeat(batch_size, 1).repeat(1, 1, input_height * input_width).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.data   grid_x
        pred_boxes[..., 1] = y.data   grid_y
        pred_boxes[..., 2] = torch.exp(w.data) * anchor_w
        pred_boxes[..., 3] = torch.exp(h.data) * anchor_h

        # 用于将输出调整为相对于416x416的大小
        _scale = torch.Tensor([stride_w, stride_h] * 2).type(FloatTensor)
        output = torch.cat((pred_boxes.view(batch_size, -1, 4) * _scale,
                            conf.view(batch_size, -1, 1), pred_cls.view(batch_size, -1, self.num_classes)), -1)
        return output.data

6、在原图上进行绘制

通过第四步,我们可以获得预测框在原图上的位置,而且这些预测框都是经过筛选的。这些筛选后的框可以直接绘制在图片上,就可以获得结果了。

7、YOLOV4的训练

7.1、YOLOV4的改进训练技巧

a)、Mosaic数据增强

Yolov4的mosaic数据增强参考了CutMix数据增强方式,理论上具有一定的相似性! CutMix数据增强方式利用两张图片进行拼接。

但是mosaic利用了四张图片,根据论文所说其拥有一个巨大的优点是丰富检测物体的背景!且在BN计算的时候一下子会计算四张图片的数据! 就像下图这样:

实现思路如下: 1、每次读取四张图片。

2、分别对四张图片进行翻转、缩放、色域变化等,并且按照四个方向位置摆好。

3、进行图片的组合和框的组合

代码语言:javascript复制
def rand(a=0, b=1):
    return np.random.rand()*(b-a)   a

def merge_bboxes(bboxes, cutx, cuty):

    merge_bbox = []
    for i in range(len(bboxes)):
        for box in bboxes[i]:
            tmp_box = []
            x1,y1,x2,y2 = box[0], box[1], box[2], box[3]

            if i == 0:
                if y1 > cuty or x1 > cutx:
                    continue
                if y2 >= cuty and y1 <= cuty:
                    y2 = cuty
                    if y2-y1 < 5:
                        continue
                if x2 >= cutx and x1 <= cutx:
                    x2 = cutx
                    if x2-x1 < 5:
                        continue

            if i == 1:
                if y2 < cuty or x1 > cutx:
                    continue

                if y2 >= cuty and y1 <= cuty:
                    y1 = cuty
                    if y2-y1 < 5:
                        continue

                if x2 >= cutx and x1 <= cutx:
                    x2 = cutx
                    if x2-x1 < 5:
                        continue

            if i == 2:
                if y2 < cuty or x2 < cutx:
                    continue

                if y2 >= cuty and y1 <= cuty:
                    y1 = cuty
                    if y2-y1 < 5:
                        continue

                if x2 >= cutx and x1 <= cutx:
                    x1 = cutx
                    if x2-x1 < 5:
                        continue

            if i == 3:
                if y1 > cuty or x2 < cutx:
                    continue

                if y2 >= cuty and y1 <= cuty:
                    y2 = cuty
                    if y2-y1 < 5:
                        continue

                if x2 >= cutx and x1 <= cutx:
                    x1 = cutx
                    if x2-x1 < 5:
                        continue

            tmp_box.append(x1)
            tmp_box.append(y1)
            tmp_box.append(x2)
            tmp_box.append(y2)
            tmp_box.append(box[-1])
            merge_bbox.append(tmp_box)
    return merge_bbox

def get_random_data(annotation_line, input_shape, random=True, hue=.1, sat=1.5, val=1.5, proc_img=True):
    '''random preprocessing for real-time data augmentation'''
    h, w = input_shape
    min_offset_x = 0.4
    min_offset_y = 0.4
    scale_low = 1-min(min_offset_x,min_offset_y)
    scale_high = scale_low 0.2

    image_datas = [] 
    box_datas = []
    index = 0

    place_x = [0,0,int(w*min_offset_x),int(w*min_offset_x)]
    place_y = [0,int(h*min_offset_y),int(w*min_offset_y),0]
    for line in annotation_line:
        # 每一行进行分割
        line_content = line.split()
        # 打开图片
        image = Image.open(line_content[0])
        image = image.convert("RGB") 
        # 图片的大小
        iw, ih = image.size
        # 保存框的位置
        box = np.array([np.array(list(map(int,box.split(',')))) for box in line_content[1:]])

        # image.save(str(index) ".jpg")
        # 是否翻转图片
        flip = rand()<.5
        if flip and len(box)>0:
            image = image.transpose(Image.FLIP_LEFT_RIGHT)
            box[:, [0,2]] = iw - box[:, [2,0]]

        # 对输入进来的图片进行缩放
        new_ar = w/h
        scale = rand(scale_low, scale_high)
        if new_ar < 1:
            nh = int(scale*h)
            nw = int(nh*new_ar)
        else:
            nw = int(scale*w)
            nh = int(nw/new_ar)
        image = image.resize((nw,nh), Image.BICUBIC)

        # 进行色域变换
        hue = rand(-hue, hue)
        sat = rand(1, sat) if rand()<.5 else 1/rand(1, sat)
        val = rand(1, val) if rand()<.5 else 1/rand(1, val)
        x = rgb_to_hsv(np.array(image)/255.)
        x[..., 0]  = hue
        x[..., 0][x[..., 0]>1] -= 1
        x[..., 0][x[..., 0]<0]  = 1
        x[..., 1] *= sat
        x[..., 2] *= val
        x[x>1] = 1
        x[x<0] = 0
        image = hsv_to_rgb(x)

        image = Image.fromarray((image*255).astype(np.uint8))
        # 将图片进行放置,分别对应四张分割图片的位置
        dx = place_x[index]
        dy = place_y[index]
        new_image = Image.new('RGB', (w,h), (128,128,128))
        new_image.paste(image, (dx, dy))
        image_data = np.array(new_image)/255

        # Image.fromarray((image_data*255).astype(np.uint8)).save(str(index) "distort.jpg")

        index = index   1
        box_data = []
        # 对box进行重新处理
        if len(box)>0:
            np.random.shuffle(box)
            box[:, [0,2]] = box[:, [0,2]]*nw/iw   dx
            box[:, [1,3]] = box[:, [1,3]]*nh/ih   dy
            box[:, 0:2][box[:, 0:2]<0] = 0
            box[:, 2][box[:, 2]>w] = w
            box[:, 3][box[:, 3]>h] = h
            box_w = box[:, 2] - box[:, 0]
            box_h = box[:, 3] - box[:, 1]
            box = box[np.logical_and(box_w>1, box_h>1)]
            box_data = np.zeros((len(box),5))
            box_data[:len(box)] = box

        image_datas.append(image_data)
        box_datas.append(box_data)

        img = Image.fromarray((image_data*255).astype(np.uint8))
        for j in range(len(box_data)):
            thickness = 3
            left, top, right, bottom  = box_data[j][0:4]
            draw = ImageDraw.Draw(img)
            for i in range(thickness):
                draw.rectangle([left   i, top   i, right - i, bottom - i],outline=(255,255,255))
        img.show()


    # 将图片分割,放在一起
    cutx = np.random.randint(int(w*min_offset_x), int(w*(1 - min_offset_x)))
    cuty = np.random.randint(int(h*min_offset_y), int(h*(1 - min_offset_y)))

    new_image = np.zeros([h,w,3])
    new_image[:cuty, :cutx, :] = image_datas[0][:cuty, :cutx, :]
    new_image[cuty:, :cutx, :] = image_datas[1][cuty:, :cutx, :]
    new_image[cuty:, cutx:, :] = image_datas[2][cuty:, cutx:, :]
    new_image[:cuty, cutx:, :] = image_datas[3][:cuty, cutx:, :]

    # 对框进行进一步的处理
    new_boxes = merge_bboxes(box_datas, cutx, cuty)

    return new_image, new_boxes

b)、Label Smoothing平滑

标签平滑的思想很简单,具体公式如下:

代码语言:javascript复制
new_onehot_labels = onehot_labels * (1 - label_smoothing)   label_smoothing / num_classes

当label_smoothing的值为0.01得时候,公式变成如下所示:

代码语言:javascript复制
new_onehot_labels = y * (1 - 0.01)   0.01 / num_classes

其实Label Smoothing平滑就是将标签进行一个平滑,原始的标签是0、1,在平滑后变成0.005(如果是二分类)、0.995,也就是说对分类准确做了一点惩罚,让模型不可以分类的太准确,太准确容易过拟合。

实现代码如下:

代码语言:javascript复制
#---------------------------------------------------#
#   平滑标签
#---------------------------------------------------#
def smooth_labels(y_true, label_smoothing,num_classes):
    return y_true * (1.0 - label_smoothing)   label_smoothing / num_classes

c)、CIOU

IoU是比值的概念,对目标物体的scale是不敏感的。然而常用的BBox的回归损失优化和IoU优化不是完全等价的,寻常的IoU无法直接优化没有重叠的部分。

于是有人提出直接使用IOU作为回归优化loss,CIOU是其中非常优秀的一种想法。

CIOU将目标与anchor之间的距离,重叠率、尺度以及惩罚项都考虑进去,使得目标框回归变得更加稳定,不会像IoU和GIoU一样出现训练过程中发散等问题。而惩罚因子把预测框长宽比拟合目标框的长宽比考虑进去。

CIOU公式如下

其中,ρ2(b,bgt)分别代表了预测框和真实框的中心点的欧式距离。c代表的是能够同时包含预测框和真实框的最小闭包区域的对角线距离。

而α和v的公式如下

把1-CIOU就可以得到相应的LOSS了。

代码语言:javascript复制
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 / (union_area   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) / (enclose_diagonal   1e-7)

    v = (4 / (math.pi ** 2)) * torch.pow((torch.atan(b1_wh[..., 0]/b1_wh[..., 1]) - torch.atan(b2_wh[..., 0]/b2_wh[..., 1])), 2)
    alpha = v / (1.0 - iou   v)
    ciou = ciou - alpha * v
    return ciou

d)、学习率余弦退火衰减

余弦退火衰减法,学习率会先上升再下降,这是退火优化法的思想。(关于什么是退火算法可以百度。)

上升的时候使用线性上升,下降的时候模拟cos函数下降。执行多次。

效果如图所示:

pytorch有直接实现的函数,可直接调用。

代码语言:javascript复制
lr_scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=5, eta_min=1e-5)

7.2、loss组成

a)、计算loss所需参数

在计算loss的时候,实际上是y_pre和y_true之间的对比:y_pre就是一幅图像经过网络之后的输出,内部含有三个特征层的内容;其需要解码才能够在图上作画y_true就是一个真实图像中,它的每个真实框对应的(19,19)、(38,38)、(76,76)网格上的偏移位置、长宽与种类。其仍需要编码才能与y_pred的结构一致实际上y_pre和y_true内容的shape都是:

(batch_size,19,19,3,85)

(batch_size,38,38,3,85)

(batch_size,76,76,3,85)

b)、y_pre是什么

网络最后输出的内容就是三个特征层每个网格点对应的预测框及其种类,即三个特征层分别对应着图片被分为不同size的网格后,每个网格点上三个先验框对应的位置、置信度及其种类。

对于输出的y1、y2、y3而言,[…, : 2]指的是相对于每个网格点的偏移量,[…, 2: 4]指的是宽和高,[…, 4: 5]指的是该框的置信度,[…, 5: ]指的是每个种类的预测概率。

现在的y_pre还是没有解码的,解码了之后才是真实图像上的情况。

c)、y_true是什么

y_true就是一个真实图像中,它的每个真实框对应的(19,19)、(38,38)、(76,76)网格上的偏移位置、长宽与种类。其仍需要编码才能与y_pred的结构一致

d)、loss的计算过程

在得到了y_pre和y_true后怎么对比呢?不是简单的减一下!loss值需要对三个特征层进行处理,这里以最小的特征层为例。

1、利用y_true取出该特征层中真实存在目标的点的位置(m,19,19,3,1)及其对应的种类(m,19,19,3,80)。

2、将prediction的预测值输出进行处理,得到reshape后的预测值y_pre,shape为(m,19,19,3,85)。还有解码后的xy,wh。

3、对于每一幅图,计算其中所有真实框与预测框的IOU,如果某些预测框和真实框的重合程度大于0.5,则忽略。

4、计算ciou作为回归的loss,这里只计算正样本的回归loss。

5、计算置信度的loss,其有两部分构成,第一部分是实际上存在目标的,预测结果中置信度的值与1对比;第二部分是实际上不存在目标的,在第四步中得到其最大IOU的值与0对比。

6、计算预测种类的loss,其计算的是实际上存在目标的,预测类与真实类的差距。

其实际上计算的总的loss是三个loss的和,这三个loss分别是:实际存在的框,CIOU LOSS。实际存在的框,预测结果中置信度的值与1对比;实际不存在的框,预测结果中置信度的值与0对比,该部分要去除被忽略的不包含目标的框。

实际存在的框,种类预测结果与实际结果的对比。

其实际代码如下:

代码语言:javascript复制

#---------------------------------------------------#
#   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 / (union_area   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) / (enclose_diagonal   1e-7)

    v = (4 / (math.pi ** 2)) * torch.pow((torch.atan(b1_wh[..., 0]/b1_wh[..., 1]) - torch.atan(b2_wh[..., 0]/b2_wh[..., 1])), 2)
    alpha = v / (1.0 - iou   v)
    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.label_smooth = label_smooth

        self.ignore_threshold = 0.5
        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 = (1 - box_ciou( pred_boxes_for_ciou[mask.bool()], t_box[mask.bool()]))* box_loss_scale[mask.bool()]

        loss_loc = torch.sum(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]][[13,26,52].index(in_w)]
        subtract_index = [0,3,6][[13,26,52].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]):
                # 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
                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]][[13,26,52].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 = 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)

            for t in range(target[i].shape[0]):
                gx = target[i][t, 0] * in_w
                gy = target[i][t, 1] * in_h
                gw = target[i][t, 2] * in_w
                gh = target[i][t, 3] * in_h
                gt_box = torch.FloatTensor(np.array([gx, gy, gw, gh])).unsqueeze(0).type(FloatTensor)

                anch_ious = bbox_iou(gt_box, pred_boxes_for_ignore, x1y1x2y2=False)
                anch_ious = anch_ious.view(pred_boxes[i].size()[:3])
                noobj_mask[i][anch_ious>self.ignore_threshold] = 0
        return noobj_mask, pred_boxes

8、测试结果展示

8.1、图片项目测试结果

希望可以帮到你

全文来自于:

https://blog.csdn.net/weixin_44791964/article/details/106214657#comments_12490737

https://github.com/bubbliiiing/yolov4-pytorch

0 人点赞