Lordon
自己实现了一个版本，测试了下阳历转农历是可以的，可以考虑考虑怎么用比较方便 #88
Hello, When I use command **python tools/plain_train_net.py --config-file configs/train_val_bs16_normal_conv.yaml** the training stage is fine, but when I try to use multi gpus to train it occus: ` python tools/plain_train_net.py --config-file...
In fact, when you make the data of gt and dt are the same one, the 3D evaluation results are not 100 ``` --label_path = kitti/label_2", --result_path = kitti/label_2", ```...
I didn't find multiple gpu training code in repro, and I found that use nn.DataParallel also does not work.
记得把 /Particle-Filter-Localization 改成/pf_localization