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

[liuhuaijjin]

Traceback (most recent call last):
File "/home/hqu/yolov5/models/yolo.py", line 274, in
model = Model(opt.cfg).to(device)
File "/home/hqu/yolov5/models/yolo.py", line 95, in init
self._initialize_biases() # only run once
File "/home/hqu/yolov5/models/yolo.py", line 150, in _initialize_biases
b[:,4] = 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.
博主，我在train过程中报这个错误，不知道怎么解决了，我的环境是RTX3090+CUDA11+pytorch1.8。跑ultralytics的yolo.py也报这个错误。

[DataXujing]

Pytorch版本太高导致的吧，可以试着降低Pytorch版本

[liuhuaijjin]

非常感谢您的回复，问题已经解决，是版本太高的原因，降到pytorch1.7就可以了

…

---Original--- From: "徐静"<[email protected]&gt; Date: Tue, Nov 17, 2020 09:49 AM To: "DataXujing/YOLO-v5"<[email protected]&gt;; Cc: "Jim"<[email protected]&gt;;"Author"<[email protected]&gt;; Subject: Re: [DataXujing/YOLO-v5] RuntimeError: a view of a leaf Variable that requires grad is being used in an in-place operation. (#23) Pytorch版本太高导致的吧，可以试着降低Pytorch版本 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[HorizonLiang]

改成这样就好了：
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