2022-10-07 15:45:56,986 adals INFO: 1 GPUs available
2022-10-07 15:45:56,987 adals INFO: Namespace(ckpt2d='@/model_2d_095000.pth', ckpt3d='@/model_3d_095000.pth', config_file='ADALS/config/nuscenes/usa2singapore/adals_sn_sgd.yaml')
2022-10-07 15:45:56,987 adals INFO: Loaded configuration file ADALS/config/nuscenes/usa2singapore/adals_sn_sgd.yaml
2022-10-07 15:45:56,987 adals INFO: Running with config:
AUTO_RESUME: True
DATALOADER:
  DROP_LAST: True
  NUM_WORKERS: 4
DATASET_SOURCE:
  NuScenesSCN:
    augmentation:
      cut_image: True
      cut_range: [512, 512]
      flip_x: 0.5
      height: 32
      noisy_rot: 0.1
      random_flip: True
      remove_large: True
      rot_z: 6.2831
      transl: True
      width: 1024
    full_scale: 4096
    lidarseg: False
    merge_classes: True
    root_dir: /data/datasets/nuScenes/nuscenes_preprocess_lidar/preprocess
    scale: 20
  TRAIN: ('train_usa',)
  TYPE: NuScenesSCN
DATASET_TARGET:
  NuScenesSCN:
    augmentation:
      cut_image: True
      cut_range: [512, 512]
      flip_x: 0.5
      height: 32
      noisy_rot: 0.1
      random_flip: True
      remove_large: True
      rot_z: 6.2831
      transl: True
      width: 1024
    full_scale: 4096
    lidarseg: False
    merge_classes: True
    root_dir: /data/datasets/nuScenes/nuscenes_preprocess_lidar/preprocess
    scale: 20
  TEST: ('test_singapore',)
  TRAIN: ('train_singapore',)
  TYPE: NuScenesSCN
  VAL: ('val_singapore',)
MODEL:
  TYPE: 
MODEL_2D:
  CKPT_PATH: 
  DUAL_HEAD: True
  NUM_CLASSES: 5
  SalsaNextSeg:
    in_channels: 5
  TYPE: SalsaNextSeg
MODEL_3D:
  CKPT_PATH: 
  DUAL_HEAD: True
  NUM_CLASSES: 5
  SCN:
    block_reps: 1
    full_scale: 4096
    in_channels: 1
    m: 16
    num_planes: 7
    residual_blocks: False
  TYPE: SCN
OPTIMIZER:
  BASE_LR: 0.001
  TYPE: 
  WEIGHT_DECAY: 0.0
OPTIMIZER_2D:
  BASE_LR: 0.01
  SGD:
    dampening: 0.0
    momentum: 0.9
  TYPE: SGD
  WEIGHT_DECAY: 0.0
OPTIMIZER_3D:
  Adam:
    betas: (0.9, 0.999)
  BASE_LR: 0.001
  TYPE: Adam
  WEIGHT_DECAY: 0.0
OPTIMIZER_DIS:
  Adam:
    betas: (0.9, 0.99)
  BASE_LR: 0.0001
  TYPE: Adam
  WEIGHT_DECAY: 0.0
OUTPUT_DIR: /workspace/DA-LPS/ADALS/output/@
RESUME_PATH: 
RESUME_STATES: True
RNG_SEED: 1
SCHEDULER:
  CLIP_LR: 0.0
  MAX_ITERATION: 100000
  MultiStepLR:
    gamma: 0.1
    milestones: (80000, 90000)
  TYPE: MultiStepLR
SCHEDULER_DIS:
  PolyLR:
    power: 0.9
  TYPE: PolyLR
TRAIN:
  ADALS:
    lambda_D_src_2d_feat: 0.1
    lambda_D_src_2d_pred: 0.1
    lambda_D_src_3d_pred: 0.1
    lambda_D_trg_2d_feat: 0.2
    lambda_D_trg_2d_pred: 0.2
    lambda_D_trg_3d_pred: 0.2
    lambda_G_trg_2d_feat: 0.02
    lambda_G_trg_2d_pred: 0.07
    lambda_G_trg_3d_pred: 0.05
    lambda_logcoral: 0.0
    lambda_minent: 0.0
    lambda_pixels: 0.5
    lambda_xm_src: 0.8
    lambda_xm_tgl: 0.0
    lambda_xm_trg: 0.1
  BATCH_SIZE: 8
  CHECKPOINT_PERIOD: 5000
  CLASS_WEIGHTS: [2.42607725, 4.61879653, 5.72875704, 3.69461499, 1.0]
  FROZEN_PATTERNS: ()
  LOG_PERIOD: 50
  MAX_TO_KEEP: 100
  SUMMARY_PERIOD: 50
VAL:
  BATCH_SIZE: 8
  KNN:
    cutoff: 1.0
    knn: 5
    search: 5
    sigma: 1.0
  LOG_PERIOD: 20
  METRIC: seg_iou
  PERIOD: 5000
2022-10-07 15:46:02,637 adals.validate INFO: Validation
2022-10-07 15:46:08,340 adals.validate INFO: iter: 1/367  seg_loss_2d_point: 0.0338 (0.0338)  seg_loss_2d_pixel: 0.0733 (0.0733)  seg_loss_3d: 0.0381 (0.0381)  time: 5.7022 (5.7022)  data: 0.7443 (0.7443)  max mem: 2853
2022-10-07 15:47:03,254 adals.validate INFO: iter: 20/367  seg_loss_2d_point: 0.0290 (0.0290)  seg_loss_2d_pixel: 0.0475 (0.0475)  seg_loss_3d: 0.0280 (0.0280)  time: 3.0308 (3.0308)  data: 0.0986 (0.0986)  max mem: 3337
2022-10-07 15:47:54,084 adals.validate INFO: iter: 40/367  seg_loss_2d_point: 0.0670 (0.0480)  seg_loss_2d_pixel: 0.0917 (0.0696)  seg_loss_3d: 0.0603 (0.0442)  time: 2.5415 (2.7862)  data: 0.0637 (0.0811)  max mem: 3650
2022-10-07 15:48:27,905 adals.validate INFO: iter: 60/367  seg_loss_2d_point: 0.0422 (0.0461)  seg_loss_2d_pixel: 0.0548 (0.0647)  seg_loss_3d: 0.0393 (0.0426)  time: 1.6911 (2.4211)  data: 0.0626 (0.0749)  max mem: 3650
2022-10-07 15:49:36,977 adals.validate INFO: iter: 80/367  seg_loss_2d_point: 0.0350 (0.0433)  seg_loss_2d_pixel: 0.0642 (0.0646)  seg_loss_3d: 0.0311 (0.0397)  time: 3.4536 (2.6792)  data: 0.0658 (0.0727)  max mem: 4852
2022-10-07 15:50:26,235 adals.validate INFO: iter: 100/367  seg_loss_2d_point: 0.0340 (0.0415)  seg_loss_2d_pixel: 0.0591 (0.0635)  seg_loss_3d: 0.0280 (0.0374)  time: 2.4629 (2.6360)  data: 0.0643 (0.0710)  max mem: 4852
2022-10-07 15:51:41,471 adals.validate INFO: iter: 120/367  seg_loss_2d_point: 0.0708 (0.0464)  seg_loss_2d_pixel: 0.0945 (0.0686)  seg_loss_3d: 0.0673 (0.0423)  time: 3.7618 (2.8236)  data: 0.0641 (0.0698)  max mem: 4971
2022-10-07 15:53:30,540 adals.validate INFO: iter: 140/367  seg_loss_2d_point: 0.0619 (0.0486)  seg_loss_2d_pixel: 0.0854 (0.0710)  seg_loss_3d: 0.0596 (0.0448)  time: 5.4535 (3.1993)  data: 0.0615 (0.0686)  max mem: 4971
2022-10-07 15:54:20,160 adals.validate INFO: iter: 160/367  seg_loss_2d_point: 0.0424 (0.0478)  seg_loss_2d_pixel: 0.0550 (0.0690)  seg_loss_3d: 0.0310 (0.0431)  time: 2.4810 (3.1095)  data: 0.0639 (0.0681)  max mem: 4971
2022-10-07 15:54:56,018 adals.validate INFO: iter: 180/367  seg_loss_2d_point: 0.0355 (0.0464)  seg_loss_2d_pixel: 0.0542 (0.0674)  seg_loss_3d: 0.0311 (0.0417)  time: 1.7929 (2.9632)  data: 0.0642 (0.0676)  max mem: 4971
2022-10-07 15:55:51,820 adals.validate INFO: iter: 200/367  seg_loss_2d_point: 0.0368 (0.0455)  seg_loss_2d_pixel: 0.0630 (0.0669)  seg_loss_3d: 0.0286 (0.0404)  time: 2.7901 (2.9459)  data: 0.0608 (0.0669)  max mem: 4971
2022-10-07 15:56:35,888 adals.validate INFO: iter: 220/367  seg_loss_2d_point: 0.0355 (0.0446)  seg_loss_2d_pixel: 0.0668 (0.0669)  seg_loss_3d: 0.0311 (0.0396)  time: 2.2034 (2.8784)  data: 0.0659 (0.0669)  max mem: 4971
2022-10-07 15:57:25,362 adals.validate INFO: iter: 240/367  seg_loss_2d_point: 0.0332 (0.0436)  seg_loss_2d_pixel: 0.0576 (0.0661)  seg_loss_3d: 0.0288 (0.0387)  time: 2.4737 (2.8447)  data: 0.0638 (0.0666)  max mem: 4971
2022-10-07 15:58:37,546 adals.validate INFO: iter: 260/367  seg_loss_2d_point: 0.0369 (0.0431)  seg_loss_2d_pixel: 0.0583 (0.0655)  seg_loss_3d: 0.0265 (0.0377)  time: 3.6092 (2.9035)  data: 0.0631 (0.0663)  max mem: 4971
2022-10-07 15:59:58,768 adals.validate INFO: iter: 280/367  seg_loss_2d_point: 0.0585 (0.0442)  seg_loss_2d_pixel: 0.0887 (0.0672)  seg_loss_3d: 0.0555 (0.0390)  time: 4.0611 (2.9862)  data: 0.0621 (0.0660)  max mem: 5081
2022-10-07 16:00:49,254 adals.validate INFO: iter: 300/367  seg_loss_2d_point: 0.0317 (0.0434)  seg_loss_2d_pixel: 0.0632 (0.0669)  seg_loss_3d: 0.0383 (0.0390)  time: 2.5243 (2.9554)  data: 0.0631 (0.0658)  max mem: 5081
2022-10-07 16:01:39,825 adals.validate INFO: iter: 320/367  seg_loss_2d_point: 0.0295 (0.0425)  seg_loss_2d_pixel: 0.0547 (0.0662)  seg_loss_3d: 0.0325 (0.0386)  time: 2.5286 (2.9287)  data: 0.0643 (0.0657)  max mem: 5081
2022-10-07 16:02:29,766 adals.validate INFO: iter: 340/367  seg_loss_2d_point: 0.0316 (0.0419)  seg_loss_2d_pixel: 0.0503 (0.0652)  seg_loss_3d: 0.0417 (0.0388)  time: 2.4970 (2.9033)  data: 0.0653 (0.0657)  max mem: 5081
2022-10-07 16:03:07,483 adals.validate INFO: iter: 360/367  seg_loss_2d_point: 0.0331 (0.0414)  seg_loss_2d_pixel: 0.0493 (0.0644)  seg_loss_3d: 0.0290 (0.0382)  time: 1.8858 (2.8468)  data: 0.0647 (0.0657)  max mem: 5081
2022-10-07 16:03:32,326 adals.validate INFO: 2D Point overall accuracy=98.77%
2022-10-07 16:03:32,326 adals.validate INFO: 2D Point overall IOU=58.02
2022-10-07 16:03:32,332 adals.validate INFO: 2D Point class-wise segmentation accuracy and IoU.
+------------------+------------+-------+----------+
| Class            |   Accuracy |   IOU |    Total |
|------------------+------------+-------+----------|
| vehicle          |      89.79 | 76.13 |  2605498 |
| pedestrian       |      69.09 | 41.45 |   244248 |
| bike             |      28.00 | 17.93 |    92887 |
| traffic_boundary |      76.16 | 55.79 |   388136 |
| background       |      99.23 | 98.80 | 98362495 |
+------------------+------------+-------+----------+
2022-10-07 16:03:32,332 adals.validate INFO: 2D Pixel overall accuracy=98.22%
2022-10-07 16:03:32,333 adals.validate INFO: 2D Pixel overall IOU=55.39
2022-10-07 16:03:32,333 adals.validate INFO: 2D Pixel class-wise segmentation accuracy and IoU.
+------------------+------------+-------+----------+
| Class            |   Accuracy |   IOU |    Total |
|------------------+------------+-------+----------|
| vehicle          |      89.81 | 72.09 |  2841525 |
| pedestrian       |      67.80 | 40.12 |   248071 |
| bike             |      27.39 | 17.19 |    98087 |
| traffic_boundary |      74.64 | 49.28 |   376372 |
| background       |      98.78 | 98.25 | 85455437 |
+------------------+------------+-------+----------+
2022-10-07 16:03:32,334 adals.validate INFO: 3D overall accuracy=98.74%
2022-10-07 16:03:32,334 adals.validate INFO: 3D overall IOU=63.43
2022-10-07 16:03:32,335 adals.validate INFO: 3D class-wise segmentation accuracy and IoU.
+------------------+------------+-------+----------+
| Class            |   Accuracy |   IOU |    Total |
|------------------+------------+-------+----------|
| vehicle          |      92.36 | 76.79 |  2605498 |
| pedestrian       |      78.71 | 56.04 |   244248 |
| bike             |      61.72 | 41.98 |    92887 |
| traffic_boundary |      77.76 | 43.56 |   388136 |
| background       |      99.07 | 98.76 | 98362495 |
+------------------+------------+-------+----------+
2022-10-07 16:03:32,335 adals.validate INFO: 2D+3D overall accuracy=99.15%
2022-10-07 16:03:32,335 adals.validate INFO: 2D+3D overall IOU=68.93
2022-10-07 16:03:32,336 adals.validate INFO: 2D+3D class-wise segmentation accuracy and IoU.
+------------------+------------+-------+----------+
| Class            |   Accuracy |   IOU |    Total |
|------------------+------------+-------+----------|
| vehicle          |      92.25 | 82.11 |  2605498 |
| pedestrian       |      76.60 | 62.43 |   244248 |
| bike             |      48.21 | 41.27 |    92887 |
| traffic_boundary |      79.26 | 59.65 |   388136 |
| background       |      99.52 | 99.18 | 98362495 |
+------------------+------------+-------+----------+
