在执行下面代码时
python train.py --img 640 --batch 16 --epochs 5 --data ./data/coco128.yaml --cfg ./models/yolov5s.yaml --weights ''
我遇到了此报错
Traceback (most recent call last):
File "train.py", line 456, in <module>
train(hyp, opt, device, tb_writer)
File "train.py", line 77, in train
model = Model(opt.cfg, ch=3, nc=nc).to(device) # create
File "C:\Users\it possible\Documents\yolov5Project\yolov5-master\models\yolo.py", line 87, in __init__
self._initialize_biases() # only run once
File "C:\Users\it possible\Documents\yolov5Project\yolov5-master\models\yolo.py", line 145, in _initialize_biases
b[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
RuntimeError: a view of a leaf Variable that requires grad is being used in an in-place operation.
解决方法
找到在File "C:\Users\it possible\Documents\yolov5Project\yolov5-master\models\yolo.py"的line 145
将代码修改为：
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
m = self.model[-1] # Detect() module
for mi, s in zip(m.m, m.stride): # from
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
with torch.no_grad():
b[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
b[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
再次测试，bug修复
本文内容由网友自发贡献，版权归原作者所有，本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容，请联系:hwhale#tublm.com(使用前将#替换为@)
