probability

Thanks！

> Thanks for your interest! It takes about 2~3 days to get ENet convergence at around epoch 20 in stage 1 and few hours in stage 2. But training in...

> Check here: https://github.com/zhyever/Monocular-Depth-Estimation-Toolbox/tree/main/splits I provide them in the `split` folder. Thanks！

> Dear author,hello.The pretrained model Voxel-MAE you proposed is very ingenious.I'm trying to replicate your work. 我做了两组实验： 实验1：SECOND训练20轮，V-M训练20轮后再训练SECOND20轮，后者效果显著好于前者。 实验2：SECOND训练200轮，V-M训练20轮后再训练SECOND200轮，前者效果好于后者。 考虑到训练过拟合，我又补充实验3：SECOND训练80轮，发现其在Car和骑行者的检测结果好于SECOND训练200轮，但是在行人检测上SECOND训练200轮效果更好。 我很疑惑，目前怀疑训练过拟合，但是我无法将loss曲线与eval准确率曲线在同一张图中可视化，无法判断合适的模型训练轮数。 请问作者如何判断模型训练恰到好处呢？ I would appreciate it if you could reply...

> Hello, why set the pre-trained model to 20 and 10 for waymo and nuscenes, is there any basis for this? And what is the pretrained epoch for KITTI? We...

> Can you release the pretraining models on these datasets? Due to the limited time, we have only released the models for Waymo dataset.

> just randomly select 50% of voxels in each scene and mask them We just randomly select 50% of voxels in each scene and mask them. The pathes in MAE...

> Hi, chaytonmin: > > Thanks for your ideas in applying MAE to 3D object detection in CP. I checked your code and noticed that some parts can be replaced...

> Hi, Thanks for the great work! I am confused about the training epoch of VoxelMAE. The pretrain epoch mentioned in the paper is 20 and 10 for Waymo and...

> 抱歉，微信群已经超过200人，不能通过二维码加群，可以加我微信i1231231