LidarGait Lidar Based Method

[wngTn]

What were the hyperparameters for the point-based methods in LidarGait? I.e., for PointNet, PointNet++, and PointTransformer?

[chuanfushen]

Triplet loss is employed with batch size at 8,8,10, refers to ID, sequence per ID, and frames number per sequence respectively.

Point number for training and testing at each frame is 512 points in lidargait paper.

SGD optimizer is with initial learning rate at 0.01, and learning rate multiply 0.1 at 2w and 3w iterations.

I will give an example configuration for pointnet++.

evaluator_cfg:
  enable_float16: true
  restore_ckpt_strict: true
  restore_hint: 40000
  save_name: PointNet2
  eval_func: evaluate_indoor_dataset
  sampler:
    batch_shuffle: false
    points_in_use:
      pointcloud_index: 0 
      points_num: 512
    batch_size: 8
    frames_num_fixed: 10 # fixed frames number for training
    frames_skip_num: 0
    #sample_type: fixed_ordered
    sample_type: all_ordered # all indicates whole sequence used to test, while ordered means input sequence by its natural order; Other options:   fixed_unordered
    frames_all_limit: 720 # limit the number of sampled frames to prevent out of memory
  metric: euc # cos
  transform:
    - type: BasePointTransform

loss_cfg:
  - loss_term_weight: 1.0
    margin: 0.2
    type: TripletLoss
    log_prefix: triplet

model_cfg:
  model: PointNet2

optimizer_cfg:
  lr: 0.01
  momentum: 0.9
  solver: SGD
  weight_decay: 0.0005

scheduler_cfg:
  gamma: 0.1
  milestones: # Learning Rate Reduction at each milestones
    - 20000
    - 30000
  scheduler: MultiStepLR
trainer_cfg:
  enable_float16: true # half_percesion float for memory reduction and speedup
  fix_BN: false
  with_test: true #true
  log_iter: 100
  restore_ckpt_strict: true
  restore_hint: 0
  save_iter: 5000
  save_name: PointNet2
  sync_BN: true
  total_iter: 40000
  sampler:
    batch_shuffle: true
    batch_size:
      - 8 # TripletSampler, batch_size[0] indicates Number of Identity
      - 8 #                 batch_size[1] indicates Samples sequqnce for each Identity
    frames_num_fixed: 10 # fixed frames number for training
    sample_type: fixed_unordered # fixed control input frames number, unordered for controlling order of input tensor; Other options: unfixed_ordered or all_ordered
    type: TripletSampler
    points_in_use:
      pointcloud_index: 0
      points_num: 512
  transform:
    - type: AllPointTransform

Noted that we follow the default model hyperparameter like https://github.com/yanx27/Pointnet_Pointnet2_pytorch/blob/master/models/pointnet2_cls_msg.py

[wngTn]

What GPU did you use for training on these point clouds? Since you'd need a forward pass with a tensor of shape (8*8*10, 3, 512). Even with automatic mixed precision, this would require significant amount of memory.

[chuanfushen]

I train PointNet++ on 8 TITAN GPUs, each with 24 GB memory.

[LlongXie]

Hi, Dr. Shen, I noticed that you use transforms like BasePointTransform and AllPointTransform when training pointnet++, but they are not included in opengait/data/transform.py. Could you please provide some details or code about PointNet++ trained on SUSTech1K? That would be much appreciated!

[chuanfushen]

Hi, Dr. Shen, I noticed that you use transforms like BasePointTransform and AllPointTransform when training pointnet++, but they are not included in opengait/data/transform.py. Could you please provide some details or code about PointNet++ trained on SUSTech1K? That would be much appreciated!

Hi, Currently, I have no time to make code publicly available. I can provide the necessary information to help you reproduce transform for point clouds.

Basically, there are only few things in PointTransform:

• Randomly sample 256/512/1024 points
• normalize point clouds https://github.com/yanx27/Pointnet_Pointnet2_pytorch/blob/eb64fe0b4c24055559cea26299cb485dcb43d8dd/data_utils/ModelNetDataLoader.py#L17C1-L22C14
• Other data augmentation for point clouds such as random jitter or translation

Hope this can help you

[LlongXie]

That's very helpful, thanks. Good luck to you!