IKAROS66

I encountered the same problem and solved it by downloading PyOpenGL and pyqt libraries in the conda virtual environment. I suspect that System dependencies were not correctly applied to the...

相同环境下，训练PMF模型没有问题，但是训练EPMF会出现值全为nan的情况，我重复训练了几次都会出现这种情况，我尝试保存最近的checkpoint文件，但是发现读取checkpoint并继续训练的时候会出现学习率并没有从之前的0.00095继续训练，而是从0.00001继续训练的，我不确定这会不会影响最终的训练效果。  这是我继续从epoch9开始训练的时候，学习率不一致的截图 

> Hello, may I ask what model of graphics card you used for training? I encountered this issue when training with a single RTX4090 . Subsequent training with a100-40GB*4 or...

> Thank you very much for your reply. It was very helpful to me. I have another question now: How long did it take you to train KITTI using vGPU32GB?...