search

spurra / vae-hands-3d

Code to evaluate model of paper "Cross-modal Deep Variational Hand Pose Estimation"
https://ait.ethz.ch/projects/2018/vae_hands/
GNU General Public License v3.0
121 stars 23 forks source link

question about type？？ #16

Open QuYJLeo opened 4 years ago

QuYJLeo commented 4 years ago

I have such a problem, do you know how to solve it, thank you

File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/linear.py", line 74, in init self.bias = Parameter(torch.Tensor(out_features)) TypeError: expected Float (got Long)

spurra commented 4 years ago

This is probably because you are using a newer pytorch version. Can you try using out_features.float()?

QuYJLeo commented 4 years ago

这可能是因为您使用的是较新的pytorch版本。您可以尝试使用out_features.float（）吗？

谢谢您解决了，我当前使用noHandInvar_noScaleInvar的model测试为何准确度并不理想，您知道原因吗？ 微信截图_20200319090839

spurra commented 4 years ago

Using no hand side invariance and no scale invariance results in the model attempting to recognize which hand side you are showing, as well as the actual scale. It is a lot more difficult. The best performing model is using both invariances.

Also, please communicate in english. I had to translate your text via google translate.

Let me know if there is anything else.

Wu-Jin-tao commented 3 years ago

This is probably because you are using a newer pytorch version. Can you try using out_features.float()?

Can I konw how do you solve the problem?? Thank you very much.