The following error was reported during my running demo.py: RuntimeError: Legacy autograd function with non-static forward method is deprecated,
smallsun1122 opened this issue · comments
smallsun1122 commented
Bian commented
I had the same problem, probably because the version of the Torch was too high, but I couldn't fix it.I wonder if you have solved this problem?
smallsun1122 commented
同学,你好,时间太久了,我有点忘记了,我在网上找了一些解决办法,看能不能帮到你,这些解决办法我看着有点熟悉 ,可能是之前用过的,希望可以帮到你。
…------------------ 原始邮件 ------------------
发件人: "Tencent/FaceDetection-DSFD" ***@***.***>;
发送时间: 2021年4月19日(星期一) 晚上8:27
***@***.***>;
抄送: "small ***@***.******@***.***>;
主题: Re: [Tencent/FaceDetection-DSFD] The following error was reported during my running demo.py: RuntimeError: Legacy autograd function with non-static forward method is deprecated, (#72)
I had the same problem, probably because the version of the Torch was too high, but I couldn't fix it.I wonder if you have solved this problem?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
Bian commented
感谢您
Wei Cui commented
I also had the same issue, can I ask how do you fix the problems? I will really appreciate it!
Berkant T. Demirtaş commented
Any answer??
Berkant T. Demirtaş commented
add @staticmethod to the beginning of the function that error has been occured.
funykatebird commented
I had the same problem, probably because the version of the Torch was too high, but I couldn't fix it.I wonder if you have solved this problem?
我也遇到了同样的问题,请问解决了吗?
Weng Shihao commented
you can easily solve this problem by:
do changes in face_ssd.py
:
output = self.detect(
face_loc.view(face_loc.size(0), -1, 4), # loc preds
self.softmax(face_conf.view(face_conf.size(0), -1, self.num_classes)), # conf preds
self.priors.type(type(x.data)) # default boxes
)
to the below code:
output = self.detect.forward(
face_loc.view(face_loc.size(0), -1, 4), # loc preds
self.softmax(face_conf.view(face_conf.size(0), -1, self.num_classes)), # conf preds
self.priors.type(type(x.data)) # default boxes
)