0 前言
我使用的GPU平台：https://cloud.videojj.com/auth/register?inviter=18452&activityChannel=student_invite
知乎：
github：https://github.com/Whiffe/yolov5-visible-and-full-person-crowdhuman
b站：https://www.bilibili.com/video/BV1KY4y1r7TQ
arxiv：
在对拥挤人群（我应用场景是学生课堂）进行检测时，采用现有的模型代码，有一定问题，比如直接采用yolov5、yolov3、faster rcnn等，在拥挤场景的检测效果不佳，但使用crowded human数据集重训练后的yolov5，效果很好。crowded human数据集标签如下，有Head BBox、Visible BBox、Full BBox。如下图显示:
在拥挤人群中的检测，我发现Full BBox会额外把其他人框进来，那么就会出现一个框里出现多个人，
这里需要些张对比图
但是我查的资料中，关于yolov5的检测结果只用了head detection和 full body detection ，并没有visible body detection。于是我使用yolov5对head detection、visible body detection进行重训练。
1 相关资料
1.1，CrowdHuman的论文
CrowdHuman: A Benchmark for Detecting Human in a Crowd：https://arxiv.org/pdf/1805.00123.pdf
1.2，yolov5-crowdhuman的代码，这里是训练后的head detection和 full body detection 的模型，并没有 visible body detection。
yolov5-crowdhuman：https://github.com/deepakcrk/yolov5-crowdhuman
1.3，这是githun中对CrowdHuman论文的翻译
PaperWeekly/CrowdHuman.md：https://github.com/Mycenae/PaperWeekly/blob/master/CrowdHuman.md
1.4，这一个博客就非常重要了，是我能完成这篇博客的核心
目标检测 YOLOv5 CrowdHuman数据集格式转YOLOv5格式：https://blog.csdn.net/flyfish1986/article/details/115485814
1.5，这个代码链接是上一个博客所使用的代码工具
YOLOv5-Tools：https://gitcode.net/mirrors/shaoshengsong/YOLOv5-Tools/-/tree/main/CrowHuman2YOLO/data
1.6 b站YOLOV5训练自己的目标检测模型的视频
手把手教你使用YOLOV5训练自己的目标检测模型：https://www.bilibili.com/video/BV1YL4y1J7xz?p=1
2 crowded human数据集下载
2.1 官网数据集下载
CrowdHuman dataset下载链接：https://www.crowdhuman.org/download.html
下载后有这些文件：
2.2 数据集上传AI平台
我用的AI平台：https://cloud.videojj.com/auth/register?inviter=18452&activityChannel=student_invite
将数据集上传到AI平台中，一般就放在：/user-data 路径下
我是讲crowded human的数据集压缩为：crowdedhuman.zip，然后上传 /user-data/crowdedHuman中，上传方法在：数据传输https://cloud.videojj.com/handbook/guide/data_manage/#%E6%95%B0%E6%8D%AE%E4%BC%A0%E8%BE%93
3 YOLOv5-Tools
3.1 YOLOv5-Tools 安装
YOLOv5-Tools的功能之一就是讲crowded human转化为yolov5可以使用的数据集格式，即coco数据集格式。
YOLOv5-Tools代码链接：https://gitcode.net/mirrors/shaoshengsong/YOLOv5-Tools
我也将这个同步到了自己的github中：https://github.com/Whiffe/YOLOv5-Tools-main
也同步到了码云：https://gitee.com/YFwinston/YOLOv5-Tools-main
在AI平台中搭建项目
pytorch:1.8.0, python:3.8, CUDA:11.1.1
cd /home
git clone https://gitee.com/YFwinston/YOLOv5-Tools-main
3.2 YOLOv5-Tools中关键文件
YOLOv5-Tools中有2个关键文件：
YOLOv5-Tools/CrowHuman2YOLO/data/prepare_vbody_data.sh
YOLOv5-Tools/CrowHuman2YOLO/data/gen_vbody_txts.py
其中我在原作者的基础上的改动如下图（gen_vbody_txts.py中的内容），主要将fbox改为了vbox
3.3 crowded human数据转化为coco数据集格式
crowded human数据转化为coco数据集格式，执行下面的代码
转化前，需要安装zip，然后将/user-data/crowdedHuman/crowdedhuman.zip复制到/home/YOLOv5-Tools-main/CrowHuman2YOLO/data/raw
apt-get update
apt-get install zip
apt-get install unzip
cp /user-data/crowdedHuman/crowdedhuman.zip /home/YOLOv5-Tools-main/CrowHuman2YOLO/data/raw
cd /home/YOLOv5-Tools-main/CrowHuman2YOLO/data/raw
unzip crowdedhuman.zip
rm crowdedhuman.zip
cd /home/YOLOv5-Tools-main/CrowHuman2YOLO/data/
bash ./prepare_vbody_data.sh 608x608
3.4 转化后的结果展示
然后目录/home/YOLOv5-Tools-main/CrowHuman2YOLO/data/raw/Images的结构如下
Images
├── 273271,1017c000ac1360b7.jpg
├── 273271,10355000e3a458a6.jpg
├── 273271,1039400091556057.jpg
├── 273271,104ec00067d5b782.jpg
├── ...
└── 284193,ff25000b6a403e9.jpg
使用文件计数命令可以数出Images文件夹下文件数量
ls -l|grep "^-"| wc -l
结果是：19370
还有个路径也有生成结果：/home/YOLOv5-Tools-main/CrowHuman2YOLO/data/crowdhuman-608x608
结构如下
crowdhuman-608x608
├── 273271,1017c000ac1360b7.jpg
├── 273271,1017c000ac1360b7.txt
├── 273271,10355000e3a458a6.jpg
├── 273271,10355000e3a458a6.txt
├── ...
├── 284193,ff25000b6a403e9.jpg
├── 284193,ff25000b6a403e9.txt
├── test.txt
└── train.txt
我们看看273271,1017c000ac1360b7.txt的内容
再看看test.txt的内容
再看看train.txt的内容
讲crowded human生成coco标准文件夹格式
3.5 图像文件和标注文本文件 重构
3.3节只是将crowded human数据集转化为了coco结构的数据集，但是图像文件和标注文本文件需要重构，
首先按照下面路径创建文件夹：
to_train_img_path = '/user-data/crowdedHuman/images/train/'
to_val_img_path = '/user-data/crowdedHuman/images/val/'
to_train_label_path = '/user-data/crowdedHuman/labels/train/'
to_val_label_path = '/user-data/crowdedHuman/labels/val/'
然后重构命令：
cd /home/YOLOv5-Tools-main/CrowHuman2YOLO/data/
python gen_coco_stru.py
结果如下：
user-data/crowdedHuman/images/
crowdedHuman
├── Images
│ ├── train
│ │ ├── 273271,1017c000ac1360b7.jpg
│ │ ├── 273271,10355000e3a458a6.jpg
│ │ ├── 273271,1039400091556057.jpg
│ │ ├── ...
│ │ └── 284193,ff01000db10348e.jpg
│ ├── val
│ │ ├── 273271,104ec00067d5b782.jpg
│ │ ├── 273271,10f400006b6fb935.jpg
│ │ ├── 273271,118910008d823f61.jpg
│ │ ├── ...
│ │ └── 284193,ff25000b6a403e9.jpg
└── labels
├── train
│ ├── 273271,1017c000ac1360b7.txt
│ ├── 273271,10355000e3a458a6.txt
│ ├── 273271,1039400091556057.txt
│ ├── ...
│ └── 284193,ff01000db10348e.txt
└── val
├── 273271,104ec00067d5b782.txt
├── 273271,10f400006b6fb935.txt
├── 273271,118910008d823f61.txt
├── ...
└── 284193,ff25000b6a403e9.txt
4 yolov5
4.1 yolov5 安装
cd /home
git clone https://gitee.com/YFwinston/yolov5.git
cd yolov5
pip install -r requirements.txt
pip install opencv-python-headless==4.1.2.30
mkdir -p /root/.config/Ultralytics
wget https://ultralytics.com/assets/Arial.ttf -O /root/.config/Ultralytics/Arial.ttf
4.2 预训练模型
我会使用预训练模型对crowded human中的head、visible body进行训练，我采用yolov5m的网络架构与预训练模型：https://github.com/ultralytics/yolov5/releases
执行下面的代码
cd /home/yolov5
mkdir pretrained
cd pretrained
wget https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5m.pt
4.3 训练
训练需要在 /home/yolov5/data 下创建：crowdhuman.yaml，其内容如下：
执行下面代码：
cd /home/yolov5/data
touch crowdhuman.yaml
train: /user-data/crowdedHuman/images/train
val: /user-data/crowdedHuman/images/val
#test: test.txt
#number of classes
nc: 2
# class names
names: ['head', 'Vperson']
执行下面的训练代码：
cd /home/yolov5/
python train.py --data ./data/crowdhuman.yaml --cfg ./models/yolov5m.yaml --weights ./pretrained/yolov5m.pt --batch-size 16 --epochs 200
4.4 demo测试
cd /home/yolov5
python ./detect.py --weights ./crowdhuman_yolov5m_visible_body.pt --source ./1.jpeg --save-txt --save-conf --hide-labels --line-thickness 4 --classes 1
4.5 训练过程与结果的截图
从结果上来看，我使用的是默认epoch，300次，但是只训练了286次，原因是第186次的训练达到最优，之后100次再也没有超过186的结果，所以训练停止。
训练时间：31.2小时
4.6 实时查看GPU，CPU和内存使用情况
如果在训练过程中，实时查看GPU，CPU和内存使用情况执行下面的代码：
pip install gpustat
gpustat -cp -i 1
4.7 分析训练结果
confusion_matrix.png
F1_curve.png
hyp.yaml
lr0: 0.01
lrf: 0.01
momentum: 0.937
weight_decay: 0.0005
warmup_epochs: 3.0
warmup_momentum: 0.8
warmup_bias_lr: 0.1
box: 0.05
cls: 0.5
cls_pw: 1.0
obj: 1.0
obj_pw: 1.0
iou_t: 0.2
anchor_t: 4.0
fl_gamma: 0.0
hsv_h: 0.015
hsv_s: 0.7
hsv_v: 0.4
degrees: 0.0
translate: 0.1
scale: 0.5
shear: 0.0
perspective: 0.0
flipud: 0.0
fliplr: 0.5
mosaic: 1.0
mixup: 0.0
copy_paste: 0.0
labels_correlogram.jpg
labels.jpg
opt.yaml
weights: ./pretrained/yolov5m.pt
cfg: ./models/yolov5m.yaml
data: ./data/crowdhuman.yaml
hyp: data/hyps/hyp.scratch-low.yaml
epochs: 300
batch_size: 16
imgsz: 640
rect: false
resume: false
nosave: false
noval: false
noautoanchor: false
noplots: false
evolve: null
bucket: ''
cache: null
image_weights: false
device: ''
multi_scale: false
single_cls: false
optimizer: SGD
sync_bn: false
workers: 8
project: runs/train
name: exp
exist_ok: false
quad: false
cos_lr: false
label_smoothing: 0.0
patience: 100
freeze:
- 0
save_period: -1
local_rank: -1
entity: null
upload_dataset: false
bbox_interval: -1
artifact_alias: latest
save_dir: runs/train/exp5
P_curve.png
PR_curve.png
R_curve.png
results.csv
epoch, train/box_loss, train/obj_loss, train/cls_loss, metrics/precision, metrics/recall, metrics/mAP_0.5,metrics/mAP_0.5:0.95, val/box_loss, val/obj_loss, val/cls_loss, x/lr0, x/lr1, x/lr2
0, 0.070957, 0.17379, 0.013804, 0.79331, 0.62187, 0.70443, 0.36578, 0.053743, 0.15582, 0.0086178, 0.0033298, 0.0033298, 0.070032
1, 0.05886, 0.1723, 0.0089482, 0.83852, 0.6577, 0.74977, 0.42579, 0.050081, 0.15285, 0.0079355, 0.0066411, 0.0066411, 0.04001
2, 0.057335, 0.17261, 0.0085512, 0.83284, 0.64311, 0.7332, 0.41763, 0.050096, 0.15692, 0.0079001, 0.0099305, 0.0099305, 0.009966
3, 0.054982, 0.17262, 0.0082141, 0.83876, 0.65609, 0.74388, 0.43208, 0.048579, 0.15438, 0.0074132, 0.009901, 0.009901, 0.009901
4, 0.053255, 0.1713, 0.007933, 0.84424, 0.6712, 0.7579, 0.45066, 0.047554, 0.15219, 0.007289, 0.009901, 0.009901, 0.009901
5, 0.052224, 0.16798, 0.0077461, 0.84808, 0.67017, 0.76022, 0.45863, 0.04693, 0.15142, 0.0071035, 0.009868, 0.009868, 0.009868
6, 0.051811, 0.16789, 0.007649, 0.85649, 0.67891, 0.76965, 0.46254, 0.046728, 0.15132, 0.0070715, 0.009835, 0.009835, 0.009835
7, 0.051141, 0.16573, 0.0075969, 0.84552, 0.68172, 0.767, 0.46258, 0.046536, 0.15094, 0.0070178, 0.009802, 0.009802, 0.009802
8, 0.050914, 0.16508, 0.0075, 0.84846, 0.69117, 0.77498, 0.471, 0.046007, 0.14988, 0.0069287, 0.009769, 0.009769, 0.009769
9, 0.050611, 0.16475, 0.0074872, 0.85132, 0.69204, 0.77705, 0.47654, 0.04582, 0.14921, 0.0068846, 0.009736, 0.009736, 0.009736
10, 0.050199, 0.163, 0.0074224, 0.85678, 0.68784, 0.77632, 0.4748, 0.045586, 0.14801, 0.0068159, 0.009703, 0.009703, 0.009703
11, 0.049954, 0.16256, 0.007362, 0.85262, 0.69381, 0.77985, 0.47737, 0.045618, 0.14902, 0.006824, 0.00967, 0.00967, 0.00967
12, 0.049833, 0.16187, 0.0073681, 0.85211, 0.6944, 0.78143, 0.47993, 0.045415, 0.14804, 0.006827, 0.009637, 0.009637, 0.009637
13, 0.049665, 0.162, 0.0073031, 0.84996, 0.69458, 0.78038, 0.48119, 0.045284, 0.14824, 0.0067918, 0.009604, 0.009604, 0.009604
14, 0.049569, 0.16097, 0.0073169, 0.85464, 0.6983, 0.78471, 0.48393, 0.045131, 0.14808, 0.0067935, 0.009571, 0.009571, 0.009571
15, 0.049421, 0.16206, 0.0072589, 0.84949, 0.70118, 0.78366, 0.48418, 0.045037, 0.14721, 0.006754, 0.009538, 0.009538, 0.009538
16, 0.049319, 0.16144, 0.0072539, 0.85332, 0.69859, 0.78399, 0.48428, 0.044933, 0.14729, 0.0067212, 0.009505, 0.009505, 0.009505
17, 0.049186, 0.1602, 0.0072142, 0.85533, 0.69967, 0.78586, 0.48799, 0.044799, 0.14681, 0.0066843, 0.009472, 0.009472, 0.009472
18, 0.04885, 0.15964, 0.007186, 0.85214, 0.70254, 0.78647, 0.4895, 0.044724, 0.14673, 0.006694, 0.009439, 0.009439, 0.009439
19, 0.049002, 0.16097, 0.0071914, 0.85537, 0.70358, 0.78861, 0.4921, 0.04452, 0.14594, 0.0066627, 0.009406, 0.009406, 0.009406
20, 0.049029, 0.1607, 0.0072433, 0.86134, 0.69844, 0.78795, 0.49224, 0.044505, 0.14587, 0.0066331, 0.009373, 0.009373, 0.009373
21, 0.048741, 0.1592, 0.0071965, 0.8593, 0.70288, 0.79033, 0.49497, 0.044323, 0.14558, 0.0066193, 0.00934, 0.00934, 0.00934
22, 0.048835, 0.15972, 0.0071411, 0.85562, 0.70757, 0.79095, 0.49551, 0.044299, 0.14547, 0.006602, 0.009307, 0.009307, 0.009307
23, 0.048565, 0.15824, 0.0071174, 0.86341, 0.70088, 0.79045, 0.49614, 0.04422, 0.14532, 0.0065856, 0.009274, 0.009274, 0.009274
24, 0.048502, 0.15836, 0.0071599, 0.87074, 0.69758, 0.79104, 0.49696, 0.044139, 0.14521, 0.0065732, 0.009241, 0.009241, 0.009241
25, 0.048553, 0.15797, 0.0071012, 0.85843, 0.707, 0.79248, 0.49898, 0.044099, 0.14496, 0.0065691, 0.009208, 0.009208, 0.009208
26, 0.048359, 0.15883, 0.007122, 0.8585, 0.70704, 0.79204, 0.50007, 0.043975, 0.14482, 0.0065442, 0.009175, 0.009175, 0.009175
27, 0.048221, 0.15749, 0.0070238, 0.85026, 0.7137, 0.79319, 0.49984, 0.043967, 0.14505, 0.0065671, 0.009142, 0.009142, 0.009142
28, 0.048238, 0.15681, 0.0071118, 0.86111, 0.7073, 0.79401, 0.50094, 0.043894, 0.14476, 0.0065535, 0.009109, 0.009109, 0.009109
29, 0.048181, 0.15668, 0.0070629, 0.86426, 0.70602, 0.79467, 0.50203, 0.043822, 0.14427, 0.0065336, 0.009076, 0.009076, 0.009076
30, 0.048216, 0.15762, 0.0070311, 0.85562, 0.71231, 0.7948, 0.50182, 0.043835, 0.14455, 0.0065325, 0.009043, 0.009043, 0.009043
31, 0.047987, 0.15609, 0.0070575, 0.86131, 0.71096, 0.79657, 0.50373, 0.043748, 0.14448, 0.0065149, 0.00901, 0.00901, 0.00901
32, 0.047937, 0.15602, 0.0069732, 0.85677, 0.7152, 0.79665, 0.50334, 0.043744, 0.14433, 0.0065135, 0.008977, 0.008977, 0.008977
33, 0.047847, 0.15598, 0.0070217, 0.8618, 0.71171, 0.79711, 0.50467, 0.043645, 0.14423, 0.0065024, 0.008944, 0.008944, 0.008944
34, 0.047701, 0.15462, 0.0069468, 0.8624, 0.71108, 0.79731, 0.50591, 0.043589, 0.14416, 0.0064981, 0.008911, 0.008911, 0.008911
35, 0.047996, 0.15686, 0.0070126, 0.86183, 0.7147, 0.79882, 0.50662, 0.043573, 0.14406, 0.0064897, 0.008878, 0.008878, 0.008878
36, 0.047757, 0.15542, 0.0069615, 0.8686, 0.70883, 0.79835, 0.5072, 0.043522, 0.14402, 0.0064837, 0.008845, 0.008845, 0.008845
37, 0.047808, 0.15439, 0.0070168, 0.85887, 0.71481, 0.79826, 0.50766, 0.043487, 0.14403, 0.0064753, 0.008812, 0.008812, 0.008812
38, 0.047862, 0.15511, 0.0069946, 0.86583, 0.71126, 0.79867, 0.50805, 0.04344, 0.14394, 0.0064749, 0.008779, 0.008779, 0.008779
39, 0.047692, 0.15519, 0.0069805, 0.86271, 0.71355, 0.79862, 0.50846, 0.043413, 0.14386, 0.0064677, 0.008746, 0.008746, 0.008746
40, 0.047726, 0.15546, 0.0069984, 0.85807, 0.71714, 0.79902, 0.50896, 0.043381, 0.14383, 0.0064706, 0.008713, 0.008713, 0.008713
41, 0.047779, 0.15582, 0.0070015, 0.86264, 0.71467, 0.79949, 0.5097, 0.043348, 0.14384, 0.0064772, 0.00868, 0.00868, 0.00868
42, 0.047656, 0.15485, 0.006979, 0.8622, 0.7161, 0.80021, 0.51011, 0.043318, 0.14389, 0.0064706, 0.008647, 0.008647, 0.008647
43, 0.047807, 0.15597, 0.0069679, 0.8668, 0.71296, 0.79999, 0.51065, 0.043248, 0.1435, 0.006448, 0.008614, 0.008614, 0.008614
44, 0.047778, 0.15477, 0.0069242, 0.8633, 0.71583, 0.80063, 0.51165, 0.043204, 0.14351, 0.0064505, 0.008581, 0.008581, 0.008581
45, 0.047605, 0.15547, 0.0069859, 0.85846, 0.71928, 0.80027, 0.51193, 0.043182, 0.14337, 0.0064418, 0.008548, 0.008548, 0.008548
46, 0.047349, 0.15388, 0.006883, 0.86237, 0.71783, 0.80084, 0.51223, 0.043162, 0.14333, 0.0064408, 0.008515, 0.008515, 0.008515
47, 0.047567, 0.15487, 0.0069349, 0.86494, 0.71538, 0.80043, 0.5124, 0.043145, 0.14338, 0.0064429, 0.008482, 0.008482, 0.008482
48, 0.047519, 0.15486, 0.0069263, 0.8617, 0.71784, 0.80049, 0.51261, 0.04312, 0.14338, 0.0064364, 0.008449, 0.008449, 0.008449
49, 0.047362, 0.15371, 0.0069242, 0.85975, 0.72024, 0.80156, 0.51333, 0.043088, 0.14333, 0.0064341, 0.008416, 0.008416, 0.008416
50, 0.04728, 0.15431, 0.0068943, 0.85967, 0.72081, 0.80192, 0.51406, 0.043058, 0.14336, 0.0064338, 0.008383, 0.008383, 0.008383
51, 0.047279, 0.1538, 0.0068735, 0.86097, 0.71983, 0.80202, 0.51456, 0.04302, 0.14332, 0.0064303, 0.00835, 0.00835, 0.00835
52, 0.047208, 0.15321, 0.0068569, 0.85493, 0.72432, 0.80241, 0.51458, 0.043011, 0.14334, 0.0064301, 0.008317, 0.008317, 0.008317
53, 0.04729, 0.15395, 0.0068912, 0.85997, 0.72122, 0.80265, 0.51475, 0.043001, 0.14337, 0.0064288, 0.008284, 0.008284, 0.008284
54, 0.047229, 0.15342, 0.0068565, 0.85811, 0.72308, 0.80314, 0.51508, 0.042978, 0.14338, 0.0064243, 0.008251, 0.008251, 0.008251
55, 0.047376, 0.15459, 0.0068981, 0.85691, 0.72414, 0.80337, 0.51553, 0.042956, 0.14336, 0.006422, 0.008218, 0.008218, 0.008218
56, 0.047211, 0.15229, 0.0068929, 0.86356, 0.71931, 0.80353, 0.51578, 0.04294, 0.14335, 0.0064176, 0.008185, 0.008185, 0.008185
57, 0.047235, 0.15381, 0.006865, 0.86825, 0.71645, 0.80376, 0.51609, 0.042923, 0.14333, 0.0064147, 0.008152, 0.008152, 0.008152
58, 0.047104, 0.15242, 0.0068455, 0.86103, 0.72192, 0.8039, 0.51625, 0.042913, 0.14333, 0.006412, 0.008119, 0.008119, 0.008119
59, 0.047212, 0.15323, 0.006855, 0.86494, 0.71918, 0.80401, 0.51631, 0.042902, 0.14332, 0.0064096, 0.008086, 0.008086, 0.008086
60, 0.047007, 0.15178, 0.0068328, 0.85997, 0.72242, 0.80392, 0.51654, 0.042889, 0.14333, 0.0064084, 0.008053, 0.008053, 0.008053
61, 0.047073, 0.15263, 0.0068762, 0.86269, 0.72077, 0.80381, 0.51667, 0.042877, 0.14334, 0.0064053, 0.00802, 0.00802, 0.00802
62, 0.046801, 0.15153, 0.0068233, 0.8637, 0.72048, 0.80398, 0.51688, 0.042864, 0.14335, 0.0064035, 0.007987, 0.007987, 0.007987
63, 0.047061, 0.15154, 0.0068429, 0.86016, 0.72362, 0.80422, 0.51701, 0.042849, 0.14333, 0.0064037, 0.007954, 0.007954, 0.007954
64, 0.046908, 0.15337, 0.0068456, 0.86257, 0.72184, 0.80426, 0.51714, 0.042835, 0.14332, 0.0064031, 0.007921, 0.007921, 0.007921
65, 0.046955, 0.15233, 0.0068139, 0.86301, 0.72003, 0.80332, 0.51732, 0.042816, 0.14311, 0.0063928, 0.007888, 0.007888, 0.007888
66, 0.046904, 0.1509, 0.0068464, 0.85974, 0.72269, 0.80354, 0.51744, 0.042811, 0.14314, 0.0063934, 0.007855, 0.007855, 0.007855
67, 0.046869, 0.1516, 0.0068431, 0.85533, 0.72629, 0.80365, 0.5175, 0.042801, 0.14314, 0.0063931, 0.007822, 0.007822, 0.007822
68, 0.046868, 0.15186, 0.0067947, 0.85644, 0.72561, 0.80384, 0.51772, 0.04279, 0.14313, 0.0063922, 0.007789, 0.007789, 0.007789
69, 0.046782, 0.15117, 0.0067815, 0.8569, 0.72548, 0.80403, 0.51787, 0.042782, 0.14314, 0.0063922, 0.007756, 0.007756, 0.007756
70, 0.046785, 0.1518, 0.0068274, 0.85587, 0.72634, 0.80402, 0.51792, 0.042775, 0.14315, 0.0063916, 0.007723, 0.007723, 0.007723
71, 0.046759, 0.15115, 0.0068609, 0.85969, 0.72378, 0.80415, 0.51817, 0.042768, 0.14315, 0.0063909, 0.00769, 0.00769, 0.00769
72, 0.046707, 0.14974, 0.0067576, 0.86053, 0.72369, 0.80434, 0.51824, 0.042761, 0.14315, 0.0063893, 0.007657, 0.007657, 0.007657
73, 0.04655, 0.15051, 0.0067876, 0.85909, 0.72499, 0.80441, 0.5184, 0.042756, 0.14316, 0.006388, 0.007624, 0.007624, 0.007624
74, 0.046614, 0.15039, 0.0067771, 0.86023, 0.72445, 0.80455, 0.5185, 0.04275, 0.14316, 0.006387, 0.007591, 0.007591, 0.007591
75, 0.046678, 0.15056, 0.0067363, 0.86038, 0.72459, 0.80469, 0.5187, 0.042745, 0.14317, 0.0063869, 0.007558, 0.007558, 0.007558
76, 0.046691, 0.15058, 0.0067379, 0.85687, 0.72697, 0.8048, 0.5187, 0.042739, 0.14318, 0.006387, 0.007525, 0.007525, 0.007525
77, 0.046798, 0.15133, 0.0068143, 0.8583, 0.72618, 0.80505, 0.5187, 0.042737, 0.1432, 0.0063875, 0.007492, 0.007492, 0.007492
78, 0.046765, 0.15115, 0.0067765, 0.85852, 0.72598, 0.8051, 0.51879, 0.04273, 0.1432, 0.0063871, 0.007459, 0.007459, 0.007459
79, 0.046523, 0.15004, 0.0068182, 0.85777, 0.72659, 0.80504, 0.51884, 0.042725, 0.14321, 0.0063862, 0.007426, 0.007426, 0.007426
80, 0.046543, 0.1492, 0.0067809, 0.85696, 0.72717, 0.80499, 0.51894, 0.042718, 0.14322, 0.0063856, 0.007393, 0.007393, 0.007393
81, 0.046543, 0.15011, 0.006765, 0.85684, 0.72763, 0.80518, 0.51911, 0.042712, 0.14321, 0.006385, 0.00736, 0.00736, 0.00736
82, 0.046375, 0.15008, 0.0067302, 0.86886, 0.71901, 0.80527, 0.51922, 0.042708, 0.14323, 0.0063849, 0.007327, 0.007327, 0.007327
83, 0.046423, 0.14981, 0.0066906, 0.85867, 0.72643, 0.80535, 0.51934, 0.042704, 0.14324, 0.0063847, 0.007294, 0.007294, 0.007294
84, 0.04648, 0.15017, 0.0067197, 0.86616, 0.72104, 0.80522, 0.51937, 0.042701, 0.14325, 0.0063841, 0.007261, 0.007261, 0.007261
85, 0.046511, 0.14933, 0.006772, 0.86853, 0.71951, 0.80529, 0.51944, 0.042695, 0.14325, 0.0063838, 0.007228, 0.007228, 0.007228
86, 0.046291, 0.14784, 0.0067385, 0.86655, 0.72096, 0.80533, 0.51954, 0.04269, 0.14327, 0.0063834, 0.007195, 0.007195, 0.007195
87, 0.046516, 0.14958, 0.0067718, 0.85308, 0.73087, 0.80533, 0.51961, 0.042686, 0.14328, 0.0063828, 0.007162, 0.007162, 0.007162
88, 0.046353, 0.15006, 0.0067302, 0.85462, 0.72999, 0.80545, 0.5197, 0.042681, 0.1433, 0.0063825, 0.007129, 0.007129, 0.007129
89, 0.046419, 0.14922, 0.0067449, 0.85495, 0.72971, 0.80542, 0.5197, 0.042678, 0.14331, 0.0063823, 0.007096, 0.007096, 0.007096
90, 0.046281, 0.14896, 0.0067095, 0.85496, 0.72978, 0.80543, 0.51976, 0.042675, 0.14332, 0.0063828, 0.007063, 0.007063, 0.007063
91, 0.046268, 0.14903, 0.0067169, 0.85552, 0.72951, 0.80544, 0.51982, 0.042671, 0.14332, 0.0063826, 0.00703, 0.00703, 0.00703
92, 0.046433, 0.14802, 0.0067417, 0.85485, 0.7302, 0.80558, 0.51997, 0.042668, 0.14333, 0.0063825, 0.006997, 0.006997, 0.006997
93, 0.046275, 0.14856, 0.0066784, 0.85481, 0.7303, 0.80566, 0.52002, 0.042665, 0.14334, 0.0063824, 0.006964, 0.006964, 0.006964
94, 0.046208, 0.14698, 0.0066624, 0.85603, 0.72958, 0.80578, 0.5201, 0.042662, 0.14335, 0.0063823, 0.006931, 0.006931, 0.006931
95, 0.046294, 0.15008, 0.0066537, 0.86223, 0.72513, 0.80575, 0.52009, 0.042658, 0.14336, 0.0063821, 0.006898, 0.006898, 0.006898
96, 0.046098, 0.14819, 0.0066551, 0.86042, 0.72639, 0.80567, 0.52012, 0.042654, 0.14336, 0.0063819, 0.006865, 0.006865, 0.006865
97, 0.046289, 0.14978, 0.0067059, 0.8609, 0.72611, 0.80576, 0.52025, 0.042652, 0.14337, 0.0063821, 0.006832, 0.006832, 0.006832
98, 0.046118, 0.14872, 0.0066771, 0.86075, 0.72623, 0.80571, 0.52025, 0.042649, 0.14338, 0.0063824, 0.006799, 0.006799, 0.006799
99, 0.046287, 0.14917, 0.0066951, 0.86722, 0.72166, 0.80574, 0.52033, 0.042647, 0.1434, 0.0063822, 0.006766, 0.006766, 0.006766
100, 0.04618, 0.14829, 0.0067279, 0.86638, 0.7224, 0.80572, 0.5203, 0.042645, 0.1434, 0.006382, 0.006733, 0.006733, 0.006733
101, 0.04599, 0.1463, 0.0066491, 0.86755, 0.72137, 0.80576, 0.52031, 0.042642, 0.14341, 0.0063814, 0.0067, 0.0067, 0.0067
102, 0.046161, 0.14791, 0.0066594, 0.86868, 0.72059, 0.80583, 0.52039, 0.042638, 0.1434, 0.0063813, 0.006667, 0.006667, 0.006667
103, 0.046044, 0.14794, 0.0066336, 0.86973, 0.71981, 0.80583, 0.52042, 0.042636, 0.14341, 0.0063814, 0.006634, 0.006634, 0.006634
104, 0.046167, 0.14893, 0.0067154, 0.86804, 0.72109, 0.80585, 0.52047, 0.042634, 0.14342, 0.0063813, 0.006601, 0.006601, 0.006601
105, 0.046118, 0.14778, 0.0066553, 0.86872, 0.72064, 0.80584, 0.52048, 0.042631, 0.14343, 0.006381, 0.006568, 0.006568, 0.006568
106, 0.046071, 0.14836, 0.0066652, 0.85837, 0.72802, 0.80579, 0.5205, 0.042629, 0.14345, 0.0063807, 0.006535, 0.006535, 0.006535
107, 0.045983, 0.14785, 0.0066074, 0.85885, 0.72771, 0.80583, 0.52054, 0.042627, 0.14347, 0.0063808, 0.006502, 0.006502, 0.006502
108, 0.046051, 0.14794, 0.006668, 0.85932, 0.72734, 0.80579, 0.52055, 0.042624, 0.14349, 0.0063809, 0.006469, 0.006469, 0.006469
109, 0.046261, 0.14925, 0.0066869, 0.86722, 0.72186, 0.80589, 0.52058, 0.042622, 0.14351, 0.006381, 0.006436, 0.006436, 0.006436
110, 0.046158, 0.14713, 0.0066534, 0.86663, 0.72234, 0.80585, 0.52064, 0.042619, 0.14352, 0.0063811, 0.006403, 0.006403, 0.006403
111, 0.045966, 0.14716, 0.0066452, 0.86749, 0.72188, 0.8059, 0.52071, 0.042614, 0.14352, 0.0063813, 0.00637, 0.00637, 0.00637
112, 0.045883, 0.14638, 0.0066409, 0.86678, 0.72246, 0.80593, 0.52075, 0.04261, 0.14353, 0.006382, 0.006337, 0.006337, 0.006337
113, 0.045908, 0.14672, 0.0066648, 0.86983, 0.7204, 0.80591, 0.52074, 0.04261, 0.14355, 0.0063825, 0.006304, 0.006304, 0.006304
114, 0.045833, 0.14749, 0.0066056, 0.86667, 0.72255, 0.80583, 0.52075, 0.042608, 0.14355, 0.0063827, 0.006271, 0.006271, 0.006271
115, 0.04586, 0.14848, 0.0066759, 0.86739, 0.72215, 0.80599, 0.52083, 0.042605, 0.14356, 0.0063833, 0.006238, 0.006238, 0.006238
116, 0.045841, 0.14705, 0.0066575, 0.86694, 0.72244, 0.80591, 0.52084, 0.042602, 0.14356, 0.0063832, 0.006205, 0.006205, 0.006205
117, 0.045686, 0.14656, 0.006567, 0.85945, 0.72785, 0.80588, 0.52087, 0.042599, 0.14357, 0.0063837, 0.006172, 0.006172, 0.006172
118, 0.04587, 0.14724, 0.0066144, 0.85938, 0.72783, 0.80593, 0.52097, 0.042599, 0.14359, 0.0063844, 0.006139, 0.006139, 0.006139
119, 0.045507, 0.14566, 0.0065791, 0.86569, 0.72325, 0.80594, 0.52095, 0.042598, 0.1436, 0.0063853, 0.006106, 0.006106, 0.006106
120, 0.045679, 0.14651, 0.0065691, 0.85915, 0.72779, 0.80589, 0.52099, 0.042597, 0.14363, 0.0063861, 0.006073, 0.006073, 0.006073
121, 0.045615, 0.14591, 0.0066026, 0.86581, 0.72318, 0.80588, 0.52104, 0.042595, 0.14364, 0.0063868, 0.00604, 0.00604, 0.00604
122, 0.045511, 0.14551, 0.0065674, 0.86011, 0.72727, 0.80588, 0.52109, 0.042595, 0.14365, 0.0063873, 0.006007, 0.006007, 0.006007
123, 0.045656, 0.14575, 0.0065647, 0.85986, 0.72732, 0.80585, 0.52109, 0.042594, 0.14366, 0.0063876, 0.005974, 0.005974, 0.005974
124, 0.045668, 0.14578, 0.0065669, 0.86277, 0.72537, 0.80587, 0.52108, 0.042593, 0.14369, 0.0063883, 0.005941, 0.005941, 0.005941
125, 0.045599, 0.14645, 0.0065404, 0.8591, 0.72809, 0.80584, 0.52107, 0.042593, 0.1437, 0.0063892, 0.005908, 0.005908, 0.005908
126, 0.045537, 0.14541, 0.0065947, 0.86645, 0.7228, 0.80593, 0.52116, 0.042589, 0.14373, 0.0063897, 0.005875, 0.005875, 0.005875
127, 0.045473, 0.14421, 0.0065542, 0.86589, 0.7233, 0.806, 0.52118, 0.042588, 0.14375, 0.0063904, 0.005842, 0.005842, 0.005842
128, 0.045618, 0.1454, 0.0065662, 0.86156, 0.7263, 0.80599, 0.52121, 0.042587, 0.14377, 0.0063918, 0.005809, 0.005809, 0.005809
129, 0.045565, 0.14595, 0.0065441, 0.86751, 0.7221, 0.80602, 0.52126, 0.042585, 0.14378, 0.0063924, 0.005776, 0.005776, 0.005776
130, 0.045589, 0.14573, 0.0065502, 0.86375, 0.72494, 0.80607, 0.52129, 0.042582, 0.14377, 0.0063926, 0.005743, 0.005743, 0.005743
131, 0.045505, 0.14484, 0.0065885, 0.86205, 0.72597, 0.80602, 0.52127, 0.042581, 0.14378, 0.0063928, 0.00571, 0.00571, 0.00571
132, 0.045533, 0.14501, 0.0065632, 0.86732, 0.72245, 0.80606, 0.52132, 0.04258, 0.1438, 0.006393, 0.005677, 0.005677, 0.005677
133, 0.045418, 0.14558, 0.0065981, 0.85937, 0.7282, 0.80605, 0.52141, 0.042578, 0.1438, 0.0063937, 0.005644, 0.005644, 0.005644
134, 0.045429, 0.14402, 0.0065531, 0.85815, 0.72885, 0.80598, 0.52137, 0.042578, 0.14384, 0.0063947, 0.005611, 0.005611, 0.005611
135, 0.045568, 0.14527, 0.0065576, 0.86679, 0.72272, 0.80602, 0.5214, 0.042576, 0.14386, 0.0063956, 0.005578, 0.005578, 0.005578
136, 0.045495, 0.14562, 0.0065343, 0.86623, 0.72326, 0.80602, 0.52143, 0.042576, 0.14388, 0.0063967, 0.005545, 0.005545, 0.005545
137, 0.045439, 0.14494, 0.0065703, 0.86654, 0.72299, 0.80594, 0.52142, 0.042575, 0.14391, 0.0063981, 0.005512, 0.005512, 0.005512
138, 0.045423, 0.14464, 0.0065369, 0.86706, 0.72278, 0.806, 0.52145, 0.042575, 0.14393, 0.006399, 0.005479, 0.005479, 0.005479
139, 0.045389, 0.14564, 0.0065522, 0.8671, 0.72269, 0.80595, 0.52148, 0.042575, 0.14395, 0.0063996, 0.005446, 0.005446, 0.005446
140, 0.045303, 0.14502, 0.0064684, 0.86831, 0.72177, 0.80596, 0.52148, 0.042575, 0.14397, 0.0064001, 0.005413, 0.005413, 0.005413
141, 0.045229, 0.14474, 0.006499, 0.86795, 0.72187, 0.80585, 0.52153, 0.042575, 0.14398, 0.0064007, 0.00538, 0.00538, 0.00538
142, 0.045191, 0.14365, 0.0064767, 0.86047, 0.72717, 0.8058, 0.52158, 0.042572, 0.14399, 0.0064013, 0.005347, 0.005347, 0.005347
143, 0.045145, 0.14448, 0.0064858, 0.85717, 0.72963, 0.80575, 0.52159, 0.042572, 0.14401, 0.0064023, 0.005314, 0.005314, 0.005314
144, 0.045166, 0.14419, 0.0065056, 0.85661, 0.73004, 0.80575, 0.52164, 0.042571, 0.14404, 0.0064034, 0.005281, 0.005281, 0.005281
145, 0.045197, 0.143, 0.0064873, 0.86115, 0.72675, 0.8058, 0.52171, 0.042569, 0.14406, 0.0064044, 0.005248, 0.005248, 0.005248
146, 0.045231, 0.1436, 0.0065185, 0.86097, 0.72705, 0.80576, 0.52173, 0.042569, 0.14409, 0.0064058, 0.005215, 0.005215, 0.005215
147, 0.045358, 0.14483, 0.0065588, 0.86189, 0.72666, 0.80582, 0.5218, 0.042568, 0.14411, 0.0064068, 0.005182, 0.005182, 0.005182
148, 0.044992, 0.14275, 0.0064692, 0.86176, 0.72675, 0.80573, 0.52181, 0.042568, 0.14414, 0.0064077, 0.005149, 0.005149, 0.005149
149, 0.045131, 0.14401, 0.0065087, 0.86151, 0.72701, 0.80573, 0.52183, 0.042567, 0.14415, 0.0064085, 0.005116, 0.005116, 0.005116
150, 0.045241, 0.14387, 0.0064921, 0.86063, 0.72744, 0.80575, 0.52188, 0.042567, 0.14418, 0.0064096, 0.005083, 0.005083, 0.005083
151, 0.045167, 0.14357, 0.0065286, 0.85798, 0.72949, 0.8057, 0.52187, 0.042567, 0.1442, 0.0064105, 0.00505, 0.00505, 0.00505
152, 0.045129, 0.14388, 0.0064399, 0.86221, 0.72648, 0.80562, 0.52193, 0.042564, 0.14421, 0.0064109, 0.005017, 0.005017, 0.005017
153, 0.045089, 0.14336, 0.0064341, 0.86168, 0.72693, 0.80553, 0.52191, 0.042564, 0.14422, 0.0064118, 0.004984, 0.004984, 0.004984
154, 0.045147, 0.14363, 0.0065227, 0.85782, 0.72984, 0.80558, 0.52204, 0.042563, 0.14426, 0.0064129, 0.004951, 0.004951, 0.004951
155, 0.044986, 0.14268, 0.0064632, 0.85814, 0.7295, 0.80556, 0.52203, 0.042562, 0.14427, 0.0064135, 0.004918, 0.004918, 0.004918
156, 0.045069, 0.14406, 0.0064597, 0.85989, 0.72748, 0.80491, 0.52211, 0.042552, 0.14411, 0.0064071, 0.004885, 0.004885, 0.004885
157, 0.045066, 0.14328, 0.0065028, 0.86187, 0.72569, 0.80457, 0.52205, 0.042552, 0.14411, 0.006407, 0.004852, 0.004852, 0.004852
158, 0.044944, 0.14343, 0.0064858, 0.86202, 0.72557, 0.80458, 0.52214, 0.042552, 0.14413, 0.0064087, 0.004819, 0.004819, 0.004819
159, 0.045022, 0.14334, 0.0064726, 0.86209, 0.72562, 0.80468, 0.52222, 0.042551, 0.14416, 0.0064097, 0.004786, 0.004786, 0.004786
160, 0.045123, 0.14379, 0.0065183, 0.86233, 0.72549, 0.80469, 0.52225, 0.042552, 0.14418, 0.0064105, 0.004753, 0.004753, 0.004753
161, 0.044895, 0.14287, 0.0064825, 0.86673, 0.7222, 0.80454, 0.52224, 0.042552, 0.14421, 0.0064114, 0.00472, 0.00472, 0.00472
162, 0.044827, 0.14215, 0.0064796, 0.866, 0.72266, 0.80441, 0.52223, 0.042554, 0.14423, 0.0064129, 0.004687, 0.004687, 0.004687
163, 0.044936, 0.14163, 0.006515, 0.86446, 0.72368, 0.8044, 0.5223, 0.042554, 0.14425, 0.0064141, 0.004654, 0.004654, 0.004654
164, 0.044873, 0.14266, 0.0064352, 0.86286, 0.72473, 0.80431, 0.52229, 0.042553, 0.14428, 0.0064157, 0.004621, 0.004621, 0.004621
165, 0.044888, 0.14265, 0.0064504, 0.8632, 0.72457, 0.80426, 0.52235, 0.042552, 0.1443, 0.0064171, 0.004588, 0.004588, 0.004588
166, 0.044756, 0.14232, 0.0064131, 0.86589, 0.72277, 0.80418, 0.52244, 0.04255, 0.14433, 0.0064186, 0.004555, 0.004555, 0.004555
167, 0.044976, 0.1433, 0.0064608, 0.86006, 0.72701, 0.8041, 0.52248, 0.042552, 0.14436, 0.0064196, 0.004522, 0.004522, 0.004522
168, 0.045015, 0.14289, 0.0064451, 0.86018, 0.72686, 0.80404, 0.52255, 0.042552, 0.1444, 0.0064211, 0.004489, 0.004489, 0.004489
169, 0.04473, 0.14101, 0.0064577, 0.86231, 0.72521, 0.80396, 0.52256, 0.042551, 0.14442, 0.0064225, 0.004456, 0.004456, 0.004456
170, 0.044721, 0.14165, 0.0064429, 0.86323, 0.72453, 0.8039, 0.52255, 0.042552, 0.14445, 0.0064237, 0.004423, 0.004423, 0.004423
171, 0.044802, 0.14234, 0.0064704, 0.86372, 0.72428, 0.80402, 0.52262, 0.042553, 0.14449, 0.0064252, 0.00439, 0.00439, 0.00439
172, 0.044771, 0.14233, 0.0064107, 0.86151, 0.72597, 0.80406, 0.52266, 0.042555, 0.14452, 0.0064265, 0.004357, 0.004357, 0.004357
173, 0.044812, 0.14097, 0.0064371, 0.86384, 0.72415, 0.80392, 0.52261, 0.042558, 0.14456, 0.0064278, 0.004324, 0.004324, 0.004324
174, 0.044744, 0.14118, 0.0064505, 0.86513, 0.7231, 0.80383, 0.52262, 0.042558, 0.14459, 0.0064293, 0.004291, 0.004291, 0.004291
175, 0.044554, 0.1417, 0.0063747, 0.86804, 0.72101, 0.80381, 0.52269, 0.042557, 0.1446, 0.0064308, 0.004258, 0.004258, 0.004258
176, 0.044597, 0.14156, 0.0063988, 0.86259, 0.72487, 0.80378, 0.52265, 0.042559, 0.14466, 0.0064323, 0.004225, 0.004225, 0.004225
177, 0.044629, 0.14148, 0.0063557, 0.8653, 0.72297, 0.80383, 0.52271, 0.042557, 0.14469, 0.0064338, 0.004192, 0.004192, 0.004192
178, 0.044694, 0.14146, 0.0064074, 0.86222, 0.72532, 0.8039, 0.52273, 0.042557, 0.14472, 0.006435, 0.004159, 0.004159, 0.004159
179, 0.044587, 0.14107, 0.0063972, 0.85598, 0.7297, 0.80387, 0.52273, 0.042557, 0.14476, 0.0064366, 0.004126, 0.004126, 0.004126
180, 0.044534, 0.14135, 0.0063952, 0.85727, 0.7289, 0.80389, 0.52282, 0.042556, 0.14479, 0.006438, 0.004093, 0.004093, 0.004093
181, 0.044619, 0.14129, 0.0063966, 0.85655, 0.72944, 0.80391, 0.52286, 0.042556, 0.14483, 0.0064396, 0.00406, 0.00406, 0.00406
182, 0.044533, 0.1418, 0.0063982, 0.86246, 0.72507, 0.80385, 0.52286, 0.042556, 0.14485, 0.0064411, 0.004027, 0.004027, 0.004027
183, 0.044427, 0.14089, 0.0063536, 0.86344, 0.72444, 0.80376, 0.5228, 0.042556, 0.14489, 0.0064425, 0.003994, 0.003994, 0.003994
184, 0.044367, 0.13974, 0.006316, 0.85939, 0.7274, 0.80376, 0.52282, 0.042557, 0.14492, 0.0064446, 0.003961, 0.003961, 0.003961
185, 0.044371, 0.14132, 0.006387, 0.86262, 0.72502, 0.8038, 0.52293, 0.042559, 0.14496, 0.006446, 0.003928, 0.003928, 0.003928
186, 0.044377, 0.14058, 0.0063399, 0.85879, 0.72766, 0.80368, 0.52289, 0.042561, 0.145, 0.0064476, 0.003895, 0.003895, 0.003895
187, 0.044294, 0.1404, 0.0063358, 0.86656, 0.72212, 0.80359, 0.52288, 0.042562, 0.14502, 0.0064487, 0.003862, 0.003862, 0.003862
188, 0.044445, 0.141, 0.00638, 0.8577, 0.72854, 0.80356, 0.52293, 0.042564, 0.14506, 0.0064499, 0.003829, 0.003829, 0.003829
189, 0.044234, 0.13952, 0.0063387, 0.85835, 0.72808, 0.8035, 0.5229, 0.042566, 0.1451, 0.0064514, 0.003796, 0.003796, 0.003796
190, 0.044196, 0.13941, 0.0063184, 0.86339, 0.72431, 0.80348, 0.52281, 0.042569, 0.14512, 0.006453, 0.003763, 0.003763, 0.003763
191, 0.044298, 0.13871, 0.0063443, 0.86331, 0.72459, 0.80353, 0.52285, 0.04257, 0.14516, 0.0064545, 0.00373, 0.00373, 0.00373
192, 0.044221, 0.13966, 0.0063447, 0.86282, 0.72494, 0.80344, 0.52284, 0.042572, 0.14521, 0.0064561, 0.003697, 0.003697, 0.003697
193, 0.044258, 0.14051, 0.006377, 0.85916, 0.72752, 0.8034, 0.52288, 0.042574, 0.14525, 0.0064574, 0.003664, 0.003664, 0.003664
194, 0.044246, 0.13959, 0.0063558, 0.86214, 0.72556, 0.80341, 0.52291, 0.042575, 0.14529, 0.0064592, 0.003631, 0.003631, 0.003631
195, 0.044257, 0.13995, 0.0063218, 0.86082, 0.72638, 0.80337, 0.5228, 0.042577, 0.14534, 0.0064615, 0.003598, 0.003598, 0.003598
196, 0.043966, 0.13728, 0.006347, 0.86047, 0.72674, 0.80341, 0.5229, 0.042579, 0.14538, 0.0064633, 0.003565, 0.003565, 0.003565
197, 0.044281, 0.13945, 0.0063819, 0.86067, 0.72674, 0.8034, 0.52294, 0.042579, 0.14542, 0.006465, 0.003532, 0.003532, 0.003532
198, 0.044237, 0.14033, 0.0063176, 0.86081, 0.72674, 0.8034, 0.52289, 0.042579, 0.14546, 0.0064662, 0.003499, 0.003499, 0.003499
199, 0.04424, 0.13925, 0.0062992, 0.86052, 0.72728, 0.80346, 0.52287, 0.042582, 0.1455, 0.006468, 0.003466, 0.003466, 0.003466
200, 0.044105, 0.13875, 0.0063296, 0.86138, 0.72651, 0.8034, 0.52285, 0.042584, 0.14556, 0.0064699, 0.003433, 0.003433, 0.003433
201, 0.044136, 0.13843, 0.0063174, 0.8615, 0.72641, 0.80339, 0.52281, 0.042586, 0.14559, 0.0064715, 0.0034, 0.0034, 0.0034
202, 0.044073, 0.13955, 0.0063003, 0.86, 0.72754, 0.80335, 0.52281, 0.042587, 0.14564, 0.006473, 0.003367, 0.003367, 0.003367
203, 0.04382, 0.13786, 0.0062683, 0.85844, 0.72872, 0.80339, 0.5228, 0.042588, 0.14568, 0.0064743, 0.003334, 0.003334, 0.003334
204, 0.043954, 0.13865, 0.0062669, 0.85793, 0.72921, 0.8034, 0.52288, 0.042593, 0.14573, 0.0064765, 0.003301, 0.003301, 0.003301
205, 0.044019, 0.13945, 0.0062609, 0.85781, 0.7293, 0.80345, 0.52283, 0.042596, 0.14577, 0.0064781, 0.003268, 0.003268, 0.003268
206, 0.044083, 0.13917, 0.0062927, 0.86592, 0.72338, 0.80343, 0.52281, 0.042598, 0.14581, 0.00648, 0.003235, 0.003235, 0.003235
207, 0.04389, 0.13819, 0.0063051, 0.86519, 0.72369, 0.80327, 0.52283, 0.0426, 0.14586, 0.0064816, 0.003202, 0.003202, 0.003202
208, 0.043906, 0.13861, 0.0062758, 0.85824, 0.72864, 0.8032, 0.52285, 0.042602, 0.1459, 0.0064836, 0.003169, 0.003169, 0.003169
209, 0.043906, 0.13868, 0.0062568, 0.86085, 0.72675, 0.80318, 0.52285, 0.042604, 0.14595, 0.006485, 0.003136, 0.003136, 0.003136
210, 0.043809, 0.13784, 0.0062523, 0.85877, 0.72826, 0.80315, 0.52283, 0.042607, 0.146, 0.0064874, 0.003103, 0.003103, 0.003103
211, 0.043841, 0.13843, 0.0062157, 0.85928, 0.72791, 0.8032, 0.5228, 0.042609, 0.14604, 0.0064894, 0.00307, 0.00307, 0.00307
212, 0.043844, 0.13805, 0.0062339, 0.86043, 0.72711, 0.80313, 0.52284, 0.042612, 0.14609, 0.0064915, 0.003037, 0.003037, 0.003037
213, 0.043776, 0.13724, 0.0062922, 0.86022, 0.72729, 0.80308, 0.52277, 0.042617, 0.14615, 0.006494, 0.003004, 0.003004, 0.003004
214, 0.043769, 0.13699, 0.0062544, 0.86082, 0.72659, 0.80306, 0.52276, 0.04262, 0.14619, 0.0064955, 0.002971, 0.002971, 0.002971
215, 0.043601, 0.13678, 0.0062546, 0.86032, 0.72702, 0.80293, 0.5228, 0.042622, 0.14624, 0.0064973, 0.002938, 0.002938, 0.002938
216, 0.043881, 0.13843, 0.0062441, 0.86103, 0.72659, 0.80289, 0.52278, 0.042624, 0.14627, 0.0064985, 0.002905, 0.002905, 0.002905
217, 0.043693, 0.13622, 0.0062642, 0.86105, 0.7266, 0.80293, 0.52278, 0.042627, 0.14632, 0.0065, 0.002872, 0.002872, 0.002872
218, 0.043789, 0.13823, 0.006247, 0.85773, 0.72894, 0.80284, 0.52278, 0.042631, 0.14637, 0.006502, 0.002839, 0.002839, 0.002839
219, 0.0437, 0.13785, 0.0061859, 0.85684, 0.72967, 0.80289, 0.52277, 0.042633, 0.14642, 0.006504, 0.002806, 0.002806, 0.002806
220, 0.043649, 0.13733, 0.0062186, 0.85832, 0.7287, 0.80284, 0.52276, 0.042636, 0.14646, 0.006506, 0.002773, 0.002773, 0.002773
221, 0.04361, 0.13685, 0.0062222, 0.85641, 0.73007, 0.80287, 0.52275, 0.042639, 0.14651, 0.0065079, 0.00274, 0.00274, 0.00274
222, 0.043666, 0.13728, 0.0062169, 0.86283, 0.72538, 0.80284, 0.52277, 0.042642, 0.14656, 0.0065097, 0.002707, 0.002707, 0.002707
223, 0.043565, 0.13632, 0.0062346, 0.86165, 0.726, 0.80276, 0.52287, 0.042643, 0.14661, 0.0065115, 0.002674, 0.002674, 0.002674
224, 0.043629, 0.13683, 0.0062235, 0.8632, 0.72504, 0.8028, 0.52289, 0.042645, 0.14666, 0.006514, 0.002641, 0.002641, 0.002641
225, 0.04362, 0.13668, 0.0062219, 0.86244, 0.72571, 0.80282, 0.52283, 0.042648, 0.14672, 0.0065162, 0.002608, 0.002608, 0.002608
226, 0.043517, 0.13639, 0.0062184, 0.8619, 0.72613, 0.80275, 0.5228, 0.042654, 0.14678, 0.0065191, 0.002575, 0.002575, 0.002575
227, 0.043529, 0.13706, 0.0061942, 0.86521, 0.72388, 0.80278, 0.5228, 0.042657, 0.14683, 0.0065211, 0.002542, 0.002542, 0.002542
228, 0.043346, 0.1348, 0.0061948, 0.86567, 0.72359, 0.80277, 0.52277, 0.042662, 0.1469, 0.0065235, 0.002509, 0.002509, 0.002509
229, 0.043533, 0.13662, 0.0062072, 0.86573, 0.72375, 0.80279, 0.52278, 0.042664, 0.14694, 0.0065254, 0.002476, 0.002476, 0.002476
230, 0.043389, 0.13552, 0.006166, 0.85958, 0.72814, 0.80275, 0.52281, 0.042666, 0.14699, 0.0065277, 0.002443, 0.002443, 0.002443
231, 0.043383, 0.13581, 0.0061759, 0.85993, 0.72779, 0.80272, 0.52281, 0.042672, 0.14705, 0.0065301, 0.00241, 0.00241, 0.00241
232, 0.043257, 0.13617, 0.0061262, 0.85932, 0.72822, 0.80267, 0.52278, 0.042675, 0.1471, 0.0065324, 0.002377, 0.002377, 0.002377
233, 0.043282, 0.13511, 0.006188, 0.86069, 0.7272, 0.80263, 0.52286, 0.042678, 0.14716, 0.0065346, 0.002344, 0.002344, 0.002344
234, 0.043389, 0.13534, 0.0061699, 0.86545, 0.72377, 0.80254, 0.52279, 0.042683, 0.14722, 0.0065369, 0.002311, 0.002311, 0.002311
235, 0.043159, 0.13643, 0.0061535, 0.86499, 0.72417, 0.80255, 0.52279, 0.042686, 0.14727, 0.006539, 0.002278, 0.002278, 0.002278
236, 0.043284, 0.13509, 0.0061199, 0.86466, 0.72442, 0.80253, 0.52282, 0.042691, 0.14734, 0.0065414, 0.002245, 0.002245, 0.002245
237, 0.043285, 0.13606, 0.0061722, 0.86456, 0.72433, 0.80243, 0.52275, 0.042695, 0.14739, 0.0065439, 0.002212, 0.002212, 0.002212
238, 0.043098, 0.13382, 0.0060997, 0.86572, 0.72349, 0.80242, 0.52274, 0.0427, 0.14744, 0.0065467, 0.002179, 0.002179, 0.002179
239, 0.043171, 0.13468, 0.0061793, 0.8652, 0.72388, 0.80243, 0.52276, 0.042705, 0.14751, 0.0065495, 0.002146, 0.002146, 0.002146
240, 0.043096, 0.13474, 0.0061341, 0.86499, 0.72419, 0.80243, 0.52273, 0.04271, 0.14757, 0.006552, 0.002113, 0.002113, 0.002113
241, 0.043107, 0.13555, 0.0061192, 0.86552, 0.72381, 0.80236, 0.52271, 0.042713, 0.14763, 0.0065543, 0.00208, 0.00208, 0.00208
242, 0.043085, 0.13431, 0.0061329, 0.86415, 0.72449, 0.80232, 0.5227, 0.042718, 0.14769, 0.0065571, 0.002047, 0.002047, 0.002047
243, 0.043142, 0.13471, 0.0061629, 0.86419, 0.72449, 0.80226, 0.52271, 0.042724, 0.14776, 0.0065597, 0.002014, 0.002014, 0.002014
244, 0.043085, 0.13495, 0.0061326, 0.86505, 0.72387, 0.80225, 0.52269, 0.04273, 0.14784, 0.0065626, 0.001981, 0.001981, 0.001981
245, 0.043149, 0.13484, 0.0060923, 0.86793, 0.722, 0.80225, 0.52265, 0.042735, 0.1479, 0.0065651, 0.001948, 0.001948, 0.001948
246, 0.042997, 0.13423, 0.006113, 0.86774, 0.72209, 0.80222, 0.52263, 0.042742, 0.14797, 0.0065684, 0.001915, 0.001915, 0.001915
247, 0.04302, 0.13449, 0.0060477, 0.86436, 0.72462, 0.80217, 0.52261, 0.042745, 0.14804, 0.006571, 0.001882, 0.001882, 0.001882
248, 0.042967, 0.13453, 0.0061085, 0.86572, 0.72383, 0.80223, 0.52256, 0.042751, 0.14811, 0.0065742, 0.001849, 0.001849, 0.001849
249, 0.042908, 0.13353, 0.0060995, 0.86778, 0.72239, 0.80215, 0.52253, 0.042758, 0.14819, 0.0065776, 0.001816, 0.001816, 0.001816
250, 0.042817, 0.13341, 0.0061048, 0.8678, 0.72231, 0.8021, 0.52244, 0.042764, 0.14825, 0.0065812, 0.001783, 0.001783, 0.001783
251, 0.042751, 0.13297, 0.0060433, 0.86773, 0.72245, 0.80199, 0.52245, 0.04277, 0.14834, 0.0065851, 0.00175, 0.00175, 0.00175
252, 0.042939, 0.13362, 0.0061333, 0.86935, 0.72124, 0.80187, 0.52232, 0.042777, 0.14841, 0.0065893, 0.001717, 0.001717, 0.001717
253, 0.042757, 0.1337, 0.006096, 0.86352, 0.7251, 0.80175, 0.52228, 0.042783, 0.14848, 0.006593, 0.001684, 0.001684, 0.001684
254, 0.042789, 0.13244, 0.0061018, 0.86351, 0.72508, 0.80168, 0.52222, 0.042789, 0.14855, 0.0065968, 0.001651, 0.001651, 0.001651
255, 0.042779, 0.13309, 0.0060419, 0.86278, 0.72561, 0.8017, 0.52224, 0.042797, 0.14863, 0.0066006, 0.001618, 0.001618, 0.001618
256, 0.042686, 0.13226, 0.0060961, 0.86476, 0.72418, 0.80158, 0.52223, 0.042803, 0.14871, 0.0066045, 0.001585, 0.001585, 0.001585
257, 0.042669, 0.13161, 0.0060629, 0.86428, 0.72455, 0.80162, 0.52219, 0.042809, 0.1488, 0.0066083, 0.001552, 0.001552, 0.001552
258, 0.042802, 0.13343, 0.0060949, 0.86409, 0.72468, 0.80157, 0.52214, 0.042817, 0.14888, 0.0066124, 0.001519, 0.001519, 0.001519
259, 0.042436, 0.1313, 0.0060102, 0.86334, 0.72512, 0.80143, 0.52205, 0.042825, 0.14895, 0.0066162, 0.001486, 0.001486, 0.001486
260, 0.042447, 0.13212, 0.005999, 0.86581, 0.72339, 0.80144, 0.522, 0.042832, 0.14903, 0.0066203, 0.001453, 0.001453, 0.001453
261, 0.042639, 0.13223, 0.0060492, 0.8657, 0.72327, 0.80134, 0.52192, 0.042838, 0.14911, 0.006624, 0.00142, 0.00142, 0.00142
262, 0.042541, 0.13077, 0.0060293, 0.86511, 0.72369, 0.80136, 0.52191, 0.042846, 0.14921, 0.0066276, 0.001387, 0.001387, 0.001387
263, 0.042435, 0.13095, 0.0060175, 0.8649, 0.72369, 0.80129, 0.52189, 0.042851, 0.14928, 0.0066308, 0.001354, 0.001354, 0.001354
264, 0.042607, 0.13251, 0.0060685, 0.86258, 0.72522, 0.80124, 0.52184, 0.042857, 0.14936, 0.0066344, 0.001321, 0.001321, 0.001321
265, 0.042471, 0.13234, 0.0060179, 0.86301, 0.72498, 0.8012, 0.52177, 0.042862, 0.14945, 0.0066381, 0.001288, 0.001288, 0.001288
266, 0.042217, 0.13064, 0.0060156, 0.86351, 0.72481, 0.80119, 0.52174, 0.042867, 0.14952, 0.0066415, 0.001255, 0.001255, 0.001255
267, 0.042332, 0.13116, 0.0060146, 0.86347, 0.72487, 0.80115, 0.52172, 0.042873, 0.14959, 0.0066447, 0.001222, 0.001222, 0.001222
268, 0.042284, 0.13117, 0.0060118, 0.86444, 0.72433, 0.80124, 0.5217, 0.04288, 0.14969, 0.0066488, 0.001189, 0.001189, 0.001189
269, 0.042337, 0.1312, 0.006001, 0.86363, 0.72502, 0.80125, 0.52167, 0.042886, 0.14977, 0.0066526, 0.001156, 0.001156, 0.001156
270, 0.042332, 0.13029, 0.0060448, 0.86372, 0.72496, 0.80112, 0.52155, 0.042895, 0.14985, 0.0066567, 0.001123, 0.001123, 0.001123
271, 0.042119, 0.13004, 0.005974, 0.86388, 0.72499, 0.801, 0.52155, 0.042902, 0.14994, 0.0066604, 0.00109, 0.00109, 0.00109
272, 0.04216, 0.12986, 0.0059309, 0.86374, 0.7251, 0.80102, 0.52145, 0.04291, 0.15003, 0.0066648, 0.001057, 0.001057, 0.001057
273, 0.04214, 0.13064, 0.00599, 0.86322, 0.72551, 0.80098, 0.52143, 0.042916, 0.15013, 0.0066693, 0.001024, 0.001024, 0.001024
274, 0.0422, 0.12908, 0.005965, 0.86193, 0.72642, 0.80101, 0.52143, 0.042923, 0.15021, 0.0066737, 0.000991, 0.000991, 0.000991
275, 0.042122, 0.12928, 0.0059814, 0.86236, 0.72614, 0.80097, 0.52138, 0.04293, 0.1503, 0.0066778, 0.000958, 0.000958, 0.000958
276, 0.042191, 0.12948, 0.0059749, 0.86064, 0.72741, 0.80098, 0.5214, 0.042937, 0.15039, 0.0066822, 0.000925, 0.000925, 0.000925
277, 0.04202, 0.12982, 0.0059551, 0.86074, 0.72748, 0.8009, 0.52131, 0.042944, 0.15049, 0.0066863, 0.000892, 0.000892, 0.000892
278, 0.042009, 0.12961, 0.0059252, 0.8618, 0.72686, 0.80077, 0.52123, 0.042951, 0.15058, 0.0066905, 0.000859, 0.000859, 0.000859
279, 0.041866, 0.12904, 0.005938, 0.86118, 0.72719, 0.80071, 0.52124, 0.042957, 0.15067, 0.0066948, 0.000826, 0.000826, 0.000826
280, 0.042011, 0.12959, 0.0059291, 0.86122, 0.72734, 0.80072, 0.52123, 0.042962, 0.15075, 0.006699, 0.000793, 0.000793, 0.000793
281, 0.041878, 0.12872, 0.0059146, 0.86195, 0.72665, 0.80071, 0.52123, 0.042967, 0.15084, 0.0067038, 0.00076, 0.00076, 0.00076
282, 0.041813, 0.12902, 0.0059217, 0.86083, 0.7274, 0.80067, 0.52122, 0.042973, 0.15093, 0.006708, 0.000727, 0.000727, 0.000727
283, 0.041877, 0.12897, 0.0059271, 0.86065, 0.72731, 0.80055, 0.52123, 0.042978, 0.15105, 0.0067123, 0.000694, 0.000694, 0.000694
284, 0.042068, 0.12974, 0.0059882, 0.86161, 0.72668, 0.80047, 0.52113, 0.042986, 0.15114, 0.0067171, 0.000661, 0.000661, 0.000661
285, 0.041859, 0.12905, 0.0059531, 0.85928, 0.72829, 0.80046, 0.5211, 0.042993, 0.15124, 0.0067214, 0.000628, 0.000628, 0.000628
results.png
train_batch0.jpg
train_batch1.jpg
train_batch2.jpg
val_batch0_labels.jpg
val_batch0_pred.jpg
val_batch1_labels.jpg
val_batch1_pred.jpg
val_batch2_labels.jpg
val_batch2_pred.jpg
5 其他目标检测网络
cd /home
git clone https://gitee.com/YFwinston/mmdetection.git
cd mmdetection
pip install mmcv-full==1.3.17 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.8.0/index.html
pip install opencv-python-headless==4.1.2.30
pip install -r requirements/build.txt
pip install -v -e .
5.1 faster rcnn
mkdir ./models
wget https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_1x_coco/faster_rcnn_r101_fpn_1x_coco_20200130-f513f705.pth -O ./models/faster_rcnn_r101_fpn_1x_coco_20200130-f513f705.pth
python ./demo/image_demo.py ./demo/1.jpeg ./configs/faster_rcnn/faster_rcnn_r101_fpn_1x_coco.py ./models/faster_rcnn_r101_fpn_1x_coco_20200130-f513f705.pth --out-file ./demo/out.jpg
可以发现，mmdetection默认的检测框大小不合适，看不清楚，所以要做修改
修改方式，我参考的：MMDetection V2.0 可视化参数修改https://blog.csdn.net/i013140225/article/details/109819366
找到mmdet/models/detectors/base.py文件，修改class BaseDetector()中的show_result()函数的输入参数
cd cd /home/mmdetection
python ./demo/image_demo.py ./demo/1.jpeg ./configs/faster_rcnn/faster_rcnn_r101_fpn_1x_coco.py ./models/faster_rcnn_r101_fpn_1x_coco_20200130-f513f705.pth --out-file ./demo/out.jpg
5.2 yolov3
cd cd /home/mmdetection
wget https://download.openmmlab.com/mmdetection/v2.0/yolo/yolov3_d53_mstrain-416_273e_coco/yolov3_d53_mstrain-416_273e_coco-2b60fcd9.pth -O ./models/yolov3_d53_mstrain-416_273e_coco-2b60fcd9.pth
python ./demo/image_demo.py ./demo/1.jpeg ./configs/yolo/yolov3_d53_mstrain-416_273e_coco.py ./models/yolov3_d53_mstrain-416_273e_coco-2b60fcd9.pth --out-file ./demo/out.jpg
5.3 yolov5
cd /home/yolov5/
wget https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5m.pt
python ./detect.py --weights ./yolov5m.pt --source ./1.jpeg --save-txt --save-conf --hide-labels --line-thickness 4 --classes 0
5.3 yolov5 (crowded human,Full body)
需要提前下载好权重：https://github.com/deepakcrk/yolov5-crowdhuman
cd /home/yolov5
python ./detect.py --weights ./crowdhuman_yolov5m_full_body.pt --source ./1.jpeg --save-txt --save-conf --hide-labels --line-thickness 4 --classes 0
5.3 yolov5 (crowded human,Visible body)
权重就是本文所训练的权重
python ./detect.py --weights ./crowdhuman_yolov5m_visible_body.pt --source ./1.jpeg --save-txt --save-conf --hide-labels --line-thickness 4 --classes 1
6 github 快速实现
6.1 yolov5-visible-and-full-person-crowdhuman
我已经把训练好的权重放在了google云盘中，需要通过github对应链接下载，然后上传到AI平台中。
github：https://github.com/Whiffe/yolov5-visible-and-full-person-crowdhuman
权重下载地址：https://drive.google.com/file/d/1VJtrdE85Wc4xSZXqAPUkWABLResUYG8V/view?usp=sharing
cd /home
git clone https://gitee.com/YFwinston/yolov5-visible-and-full-person-crowdhuman.git
cd yolov5-visible-and-full-person-crowdhuman
pip install -r requirements.txt
pip install opencv-python-headless==4.1.2.30
mkdir -p /root/.config/Ultralytics
wget https://ultralytics.com/assets/Arial.ttf -O /root/.config/Ultralytics/Arial.ttf
6.2 demo测试
检测头与身体
python ./detect.py --weights ./crowdhuman_vbody_yolov5m.pt --source ./1.jpeg --save-txt --save-conf
检测visible body
Test (Only Visible Person Class)
python ./detect.py --weights ./crowdhuman_vbody_yolov5m.pt --source ./1.jpeg --save-txt --save-conf --classes 1
检测头
Test (Only Heads)
python ./detect.py --weights ./crowdhuman_vbody_yolov5m.pt --source ./1.jpeg --save-txt --save-conf --classes 0
1004
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
