RuntimeError: a view of a leaf Variable that requires grad is being used in an in-place operation.

[EslamHaourn]

[W NNPACK.cpp:80] Could not initialize NNPACK! Reason: Unsupported hardware.
Traceback (most recent call last):
File "train.py", line 468, in
train(hyp, tb_writer, opt, device)
File "train.py", line 80, in train
model = Model(opt.cfg, nc=nc).to(device)
File "/home/eslam/kitti_3parts/PyTorch_YOLOv4-u5/models/yolo.py", line 74, in init
self._initialize_biases() # only run once
File "/home/eslam/kitti_3parts/PyTorch_YOLOv4-u5/models/yolo.py", line 131, 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.

Hello,
This error prevent training to start.
Could you help me know the mistake I do?
kindly, help me. Any help would be appreciated.
Thanks in advance.

[dhhdjsmsl]

add with torch.no_grad(): above b[:, 4]+=math.log()....