MRmr

> > Now that I've solved this problem, "scannetv2_seg_dataset_rgb21c_pointid.py" simply requires "_vh_clean_2.notes.ply" and "_vh_clean_2.ply."So we only need to download these two types of files in "scannet," and they only use...

> @MR-hyj Can you please tell me , do you face any problem running the control module? it not working fine when I run it with Carla and I don't...

> @MR-hyj Can you please give me your email, I would like to ask you some questions regarding Carla and Apollo, if you don't mind. Sure. It's [email protected]

By the way, I tried set `num_neighbors=3`, slower as it is, `ppf` still achieves the same accuracy with more epochs. But in this case, `pmd` is much worse. So definitely...

> Hello, I didn't try any additional features. The PPF is a natural choice since it comes from PPFNet, which was based on traditional descriptors (PFH/FPFH). > > Your pmd...

`pipeline` contains preprocessors of dataset such as augmentation. try ```python train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict(type='Resize', img_scale=(750, 1101), keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict(type='Normalize', **img_norm_cfg), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img',...

> Hi, I have the same problem, how can I get the `.pth` file for the student model ONLY ? > > I made the same observation as @MR-hyj: the...