fighting!

这个应该是你torch 把呢不能问题，卸载重装一下

of course ,U only add the bbox head. I will realize after my work will be done.

because my GPU(8G)， so in here I use 3*3,U can modify it by yourself

Thank you your issue. I will change it soon

I try , at the begin of training the loss is 16 ,at the end of epoch the loss is 4.0

I also face this problem. Do you fix it ?

I also have the above problems

And,also, when I delete the ```python rendered_seq, aux_seq = self.eval() ``` in train.py, the question do not happen. I am very confused about the problem.

Of course, I create conda environment based on your misc/banmo-cu113.yml. The other problem is when i run # mode: fine tunning without pose correction I see this problem, due to...

Thank you for your kind reply the log of issue of training: ``` /home/lingteng/anaconda3/envs/banmo-cu113/lib/python3.9/site-packages/numpy/core/_methods.py:189: RuntimeWarning: invalid value encountered in double_scalars ret = ret.dtype.type(ret / rcount) Traceback (most recent call last):...