The following error was reported during my running demo.py: RuntimeError: Legacy autograd function with non-static forward method is deprecated，

Question

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 4 years ago · comments

smallsun1122 commented 4 years ago

Bian commented 3 years ago

感谢您

Bian · Answer 1 · Mon Apr 19 2021 20:27:39 GMT+0800 (China Standard Time)

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 · Answer 2 · Mon Apr 19 2021 22:28:50 GMT+0800 (China Standard Time)

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.

Wei Cui · Answer 3 · Wed May 19 2021 01:37:36 GMT+0800 (China Standard Time)

I also had the same issue, can I ask how do you fix the problems? I will really appreciate it!

Berkant T. Demirtaş · Answer 4 · Mon Sep 20 2021 04:18:05 GMT+0800 (China Standard Time)

Any answer??

Berkant T. Demirtaş · Answer 5 · Mon Sep 20 2021 05:43:57 GMT+0800 (China Standard Time)

add @staticmethod to the beginning of the function that error has been occured.

funykatebird · Answer 6 · Thu May 12 2022 16:55:41 GMT+0800 (China Standard Time)

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 · Answer 7 · Thu Aug 18 2022 03:23:04 GMT+0800 (China Standard Time)

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
                )