Closed EvaneSnow closed 3 years ago
@WeijingShi 希望得到你的回复,谢谢
Hi @EvaneSnow, Thanks for your interest in our work.
python3 run.py checkpoints/car_auto_T3_trainval/ --test --dataset_root_dir DATASET_ROOT_DIR --output_dir DIR_TO_SAVE_RESULTS
.Hope it helps.
@WeijingShi 谢谢你的回答,我看你的用户名应该也是中国人,我就不使用英语和你交流了,抱歉哈。我是刚接触点云预测网络,偶然看到你发表在CVPR上的论文,很有兴趣。我想问哈,如果我使用这条命令进行训练:
python3 train.py configs/car_auto_T3_train_train_config configs/car_auto_T3_train_config
那么,我的训练类别是只有车这一类吗?能不能将车,人一起进行训练?
我在你的car_auto_T3_train_train_config文件中发现,num_classes:4,这是说明有4类车吗?
希望得到您的回复,谢谢。
@EvaneSnow, Sure, no problem. Currently, we use separate checkpoints for cars and pedestrians, but you can try to combine them into one. The num_classes=4
contains the background, side-view car, front/back-view car, and other vehicles.
@WeijingShi 谢谢你的回答,如果我想在前向推理过程中,看到如你论文中的三维框,二维框,
是不是需要设置python3 run.py checkpoints/car_auto_T3_train/ --dataset_root_dir DATASET_ROOT_DIR --output_dir DIR_TO_SAVE_RESULTS --level 1
将--level的值设置为1.
Yes, that's correct. You can also set level
to 2 to view the results one by one.
@WeijingShi 非常感谢你的回答,谢谢你,祝你学术事业双丰收。
@WeijingShi 我最后还有一个小问题,我看你论文中,前向推理,可以同时检测车,人
如果我也想在同一张点云上同时检测车,人,如何操作呢?
因为我看项目中的权重,车和人的权重参数是分开保存的,那进行权重加载时,如何进行操作?
Hi @EvaneSnow, The simplest way is to run two models independently on the same inputs and then put their results together. Of course, putting all classes into one network and re-train would be a better method. Best wishes to you as well!
真是太感谢你啦,我目前已经没有问题啦