Skip to content

Y
yolov7-obb

Tc.小浩 / yolov7-obb
与 Fork 源项目一致

从无法访问的项目Fork

通知 1
Star 0
Fork 0
Y
yolov7-obb

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

提交 6b5ec0ad 编写于 作者: _白鹭先生_'s avatar _白鹭先生_
浏览文件
操作

修改voc

上级 e0535031
展开全部 隐藏空白更改
内联 并排
Showing with 1053 addition and 9 deletion
2007_train.txt 0 → 100644
浏览文件 @ 6b5ec0ad
此差异已折叠。
2007_val.txt 0 → 100644
浏览文件 @ 6b5ec0ad
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000003.jpg 103,217,87,25,79.01934814453125,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000017.jpg 107,232,14,54,83.1572265625,0 388,118,11,56,87.61405944824219,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000047.jpg 150,162,65,18,66.19405364990234,0 304,227,9,18,28.610462188720703,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000050.jpg 59,153,29,10,66.80140686035156,0 265,87,30,10,83.6598129272461,0 168,273,26,10,69.44395446777344,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000052.jpg 170,136,88,22,72.25532531738281,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000055.jpg 206,146,124,31,5.389311790466309,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000060.jpg 158,75,49,16,90.0,0 212,247,47,21,85.60128784179688,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000061.jpg 94,96,14,39,17.447187423706055,0 366,118,16,50,0.0,0 38,200,30,12,75.96376037597656,0 421,291,49,24,86.98721313476562,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000065.jpg 217,58,26,75,13.815024375915527,0 106,272,73,30,90.0,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000075.jpg 188,149,85,22,78.69007110595703,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000079.jpg 156,65,44,14,67.16634368896484,0 331,273,45,15,68.96248626708984,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000102.jpg 198,164,25,103,70.75047302246094,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000104.jpg 227,227,18,101,68.19859313964844,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000111.jpg 55,132,26,10,74.05460357666016,0 231,72,31,11,81.8698959350586,0 149,236,24,12,80.53767395019531,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000120.jpg 162,138,48,13,77.90524291992188,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000122.jpg 111,146,68,17,85.2363510131836,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000130.jpg 269,164,30,91,1.3322198390960693,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000148.jpg 234,229,9,32,0.0,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000171.jpg 42,52,21,10,80.53767395019531,0 184,206,22,9,82.40535736083984,0 346,140,31,7,78.69007110595703,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000177.jpg 58,48,38,8,85.60128784179688,0 257,29,25,9,84.2894058227539,0 400,181,29,9,82.40535736083984,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000180.jpg 52,174,49,12,74.05460357666016,0 158,58,31,9,85.91438293457031,0 281,220,44,10,67.83365631103516,0 400,83,24,9,77.00537872314453,0 127,196,50,7,78.69007110595703,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000202.jpg 211,125,33,10,4.969741344451904,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000228.jpg 170,280,84,19,7.969610214233398,0 420,306,31,16,8.746162414550781,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000239.jpg 258,99,32,140,25.676815032958984,0 165,272,31,177,30.25643539428711,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000248.jpg 76,157,26,12,84.80557250976562,0 47,214,14,6,81.8698959350586,0 211,170,25,8,85.2363510131836,0 239,257,28,11,82.87498474121094,0 366,71,13,34,42.87889862060547,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000251.jpg 174,103,15,50,77.47119140625,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000264.jpg 289,56,12,29,0.0,0 260,112,6,14,0.0,0 246,207,8,19,0.0,0 424,68,25,10,86.633544921875,0 451,155,27,12,81.8698959350586,0 24,17,8,24,66.03750610351562,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000276.jpg 58,118,157,31,79.87532806396484,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000277.jpg 165,48,42,15,79.69515228271484,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000279.jpg 199,217,46,15,76.60750579833984,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000280.jpg 129,265,54,15,85.36454010009766,0 439,111,45,15,77.47119140625,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000297.jpg 41,34,27,12,78.69007110595703,0 73,134,33,14,85.2363510131836,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000300.jpg 143,61,17,43,55.00797653198242,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000310.jpg 462,251,104,21,75.3791275024414,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000315.jpg 121,39,49,17,79.99201965332031,0 449,393,52,16,80.53767395019531,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000323.jpg 139,149,48,16,77.27564239501953,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000326.jpg 87,245,69,17,82.40535736083984,0 446,63,57,19,80.53767395019531,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000335.jpg 248,12,47,15,8.880660057067871,0 424,73,19,9,8.130102157592773,0 406,156,13,53,68.83873748779297,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000360.jpg 272,75,31,10,75.96376037597656,0 240,298,43,14,79.3803482055664,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000372.jpg 47,43,53,12,74.74488067626953,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000390.jpg 104,71,20,69,0.0,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000394.jpg 84,181,14,49,66.25050354003906,0 105,98,14,10,0.0,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000395.jpg 292,95,48,13,3.1798300743103027,0 448,239,13,48,64.98310089111328,0 468,156,9,12,83.6598129272461,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000411.jpg 108,118,134,49,87.27368927001953,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000433.jpg 93,114,102,32,78.40782928466797,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000434.jpg 250,182,197,32,75.3236083984375,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000440.jpg 61,159,151,38,71.56504821777344,0 399,224,216,30,78.36637115478516,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000452.jpg 84,146,89,30,77.82854461669922,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000457.jpg 157,283,24,62,44.02898025512695,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000482.jpg 103,127,106,33,84.68545532226562,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000513.jpg 432,190,96,12,72.58203125,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000515.jpg 71,229,92,13,71.56505584716797,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000532.jpg 64,75,25,68,1.060911774635315,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000540.jpg 334,203,51,137,1.7183579206466675,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000553.jpg 429,222,19,58,11.309932708740234,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000561.jpg 290,201,36,112,8.637131690979004,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000571.jpg 261,194,139,49,89.4791488647461,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000572.jpg 109,155,50,140,1.5207698345184326,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000594.jpg 283,143,122,25,6.709836483001709,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000609.jpg 203,182,25,100,83.8844985961914,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000613.jpg 339,132,25,97,84.03550720214844,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000618.jpg 229,165,26,102,83.0887680053711,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000649.jpg 153,304,8,21,50.19443130493164,0 153,49,29,6,69.44395446777344,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000656.jpg 95,139,33,7,77.90524291992188,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000662.jpg 40,81,59,8,70.55996704101562,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000671.jpg 445,220,15,41,50.19443130493164,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000672.jpg 213,288,47,12,69.44395446777344,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000675.jpg 411,269,39,11,68.19859313964844,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000700.jpg 287,140,22,57,4.39870548248291,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000719.jpg 459,246,20,55,10.954063415527344,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000745.jpg 185,166,155,28,12.464933395385742,0 45,140,69,18,16.990825653076172,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000749.jpg 125,153,104,19,11.309932708740234,0 119,170,106,19,17.447187423706055,0 114,188,106,20,19.290042877197266,0 320,200,229,29,11.592175483703613,0 353,230,153,20,11.16487979888916,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000752.jpg 144,87,140,40,56.09372329711914,0 245,252,210,59,65.62352752685547,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000753.jpg 183,148,28,113,81.52884674072266,0 376,291,13,41,78.69007110595703,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000770.jpg 320,179,30,13,56.3099365234375,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000795.jpg 202,65,12,29,0.0,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000838.jpg 352,124,55,31,77.47119140625,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000855.jpg 250,177,77,12,83.6598129272461,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000917.jpg 351,117,13,65,3.8140745162963867,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000918.jpg 350,162,68,25,36.02737045288086,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000922.jpg 398,136,40,17,53.74616622924805,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000927.jpg 259,141,25,51,53.130104064941406,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000932.jpg 225,127,85,29,47.41950988769531,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000941.jpg 336,132,22,56,0.0,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000946.jpg 245,159,62,23,32.905242919921875,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000951.jpg 432,142,10,31,86.42366790771484,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000954.jpg 184,260,19,53,71.56505584716797,0 226,88,31,20,68.19859313964844,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000966.jpg 125,119,9,34,8.972626686096191,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000967.jpg 391,165,8,34,7.431407928466797,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000971.jpg 201,67,12,25,52.12501525878906,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000993.jpg 112,176,83,38,45.0,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/000996.jpg 147,180,47,24,46.636573791503906,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001019.jpg 198,120,12,39,46.218875885009766,0 143,217,38,13,-0.0,0 49,142,29,12,18.434947967529297,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001022.jpg 255,226,26,13,45.0,0 447,139,22,47,77.47119140625,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001044.jpg 310,116,16,32,86.98721313476562,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001054.jpg 305,115,7,21,90.0,0 420,233,5,21,85.2363510131836,0 329,269,6,19,78.69007110595703,0 217,210,6,14,82.87498474121094,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001058.jpg 196,62,24,7,-0.0,0 311,180,5,21,90.0,0 221,217,6,20,90.0,0 108,157,5,15,90.0,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001074.jpg 155,132,9,16,81.8698959350586,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001078.jpg 172,92,42,20,63.43495178222656,0 153,161,12,22,0.0,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001099.jpg 64,163,12,28,0.0,0 163,55,9,20,0.0,0 142,200,12,28,0.0,0 193,142,10,20,-0.0,0 242,127,17,9,80.53767395019531,0 303,135,10,17,-0.0,0 344,76,20,11,69.44395446777344,0 269,234,15,33,59.03623962402344,0 273,258,14,26,35.53767395019531,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001102.jpg 57,24,7,18,5.19442892074585,0 34,171,26,13,90.0,0 87,114,10,20,0.0,0 135,98,18,12,90.0,0 162,205,17,34,53.13010025024414,0 166,228,16,28,50.19443130493164,0 196,107,9,17,0.0,0 237,47,19,10,63.43495178222656,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001128.jpg 69,77,27,11,15.945395469665527,0 86,164,32,9,15.945395469665527,0 214,82,42,11,22.61986541748047,0 202,221,29,10,18.434947967529297,0 326,158,29,10,16.699243545532227,0 392,82,28,11,21.80141258239746,0 426,156,26,11,15.945395469665527,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001133.jpg 261,76,41,13,3.3664605617523193,0 156,170,22,10,9.462322235107422,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001145.jpg 62,76,23,8,-0.0,0 397,121,18,7,12.528807640075684,0
D:\Notebook\yolov7-pytorch\VOCdevkit/VOC2007/JPEGImages/001158.jpg 104,31,25,7,28.610462188720703,0 36,72,19,7,14.03624439239502,0 34,127,16,7,8.130102157592773,0 87,157,16,6,7.125016689300537,0 226,141,8,19,73.3007583618164,0
train.py
浏览文件 @ 6b5ec0ad
......@@ -41,7 +41,7 @@ if __name__ == "__main__":
# Cuda 是否使用Cuda
# 没有GPU可以设置成False
#---------------------------------#
Cuda = True
Cuda = False
#---------------------------------------------------------------------#
# distributed 用于指定是否使用单机多卡分布式运行
# 终端指令仅支持Ubuntu。CUDA_VISIBLE_DEVICES用于在Ubuntu下指定显卡。
......@@ -67,7 +67,7 @@ if __name__ == "__main__":
# classes_path 指向model_data下的txt，与自己训练的数据集相关
# 训练前一定要修改classes_path，使其对应自己的数据集
#---------------------------------------------------------------------#
classes_path = 'model_data/voc_classes.txt'
classes_path = 'model_data/ssdd_classes.txt'
#---------------------------------------------------------------------#
# anchors_path 代表先验框对应的txt文件，一般不修改。
# anchors_mask 用于帮助代码找到对应的先验框，一般不修改。
......@@ -93,7 +93,7 @@ if __name__ == "__main__":
# 可以设置mosaic=True，直接随机初始化参数开始训练，但得到的效果仍然不如有预训练的情况。（像COCO这样的大数据集可以这样做）
# 2、了解imagenet数据集，首先训练分类模型，获得网络的主干部分权值，分类模型的 主干部分 和该模型通用，基于此进行训练。
#----------------------------------------------------------------------------------------------------------------------------#
model_path = 'model_data/yolov7_weights.pth'
model_path = ''
#------------------------------------------------------#
# input_shape 输入的shape大小，一定要是32的倍数
#------------------------------------------------------#
......@@ -124,9 +124,9 @@ if __name__ == "__main__":
# 当mosaic=True时，本代码会在special_aug_ratio范围内开启mosaic。
# 默认为前70%个epoch，100个世代会开启70个世代。
#------------------------------------------------------------------#
mosaic = True
mosaic = False
mosaic_prob = 0.5
mixup = True
mixup = False
mixup_prob = 0.5
special_aug_ratio = 0.7
#------------------------------------------------------------------#
......@@ -186,7 +186,7 @@ if __name__ == "__main__":
# Freeze_Train 是否进行冻结训练
# 默认先冻结主干训练后解冻训练。
#------------------------------------------------------------------#
Freeze_Train = True
Freeze_Train = False
#------------------------------------------------------------------#
# 其它训练参数：学习率、优化器、学习率下降有关
......
voc_annotation.py
浏览文件 @ 6b5ec0ad
......@@ -20,7 +20,7 @@ annotation_mode = 0
# 那么就是因为classes没有设定正确
# 仅在annotation_mode为0和2的时候有效
#-------------------------------------------------------------------#
classes_path = 'model_data/voc_classes.txt'
classes_path = 'model_data/ssdd_classes.txt'
#--------------------------------------------------------------------------------------------------------------------------------#
# trainval_percent用于指定(训练集+验证集)与测试集的比例，默认情况下 (训练集+验证集):测试集 = 9:1
# train_percent用于指定(训练集+验证集)中训练集与验证集的比例，默认情况下 训练集:验证集 = 9:1
......@@ -55,8 +55,8 @@ def convert_annotation(year, image_id, list_file):
if cls not in classes or int(difficult)==1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (int(float(xmlbox.find('xmin').text)), int(float(xmlbox.find('ymin').text)), int(float(xmlbox.find('xmax').text)), int(float(xmlbox.find('ymax').text)))
xmlbox = obj.find('rotated_bndbox')
b = (int(float(xmlbox.find('rotated_bbox_cx').text)), int(float(xmlbox.find('rotated_bbox_cy').text)), int(float(xmlbox.find('rotated_bbox_w').text)), int(float(xmlbox.find('rotated_bbox_h').text)), float(xmlbox.find('rotated_bbox_theta').text))
list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))
nums[classes.index(cls)] = nums[classes.index(cls)] + 1
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或