Pointcept/configs/nuscenes/semseg-spunet-v1m1-0-base.py

_base_ = ["../_base_/default_runtime.py"]

# misc custom setting
batch_size = 12  # bs: total bs in all gpus
mix_prob = 0
empty_cache = False
enable_amp = True

# model settings
model = dict(
    type="DefaultSegmentor",
    backbone=dict(
        type="SpUNet-v1m1",
        in_channels=4,
        num_classes=16,
        channels=(32, 64, 128, 256, 256, 128, 96, 96),
        layers=(2, 3, 4, 6, 2, 2, 2, 2),
    ),
    criteria=[dict(type="CrossEntropyLoss", loss_weight=1.0, ignore_index=-1)],
)

# scheduler settings
epoch = 50
eval_epoch = 50
optimizer = dict(type="AdamW", lr=0.002, weight_decay=0.005)
scheduler = dict(
    type="OneCycleLR",
    max_lr=optimizer["lr"],
    pct_start=0.04,
    anneal_strategy="cos",
    div_factor=10.0,
    final_div_factor=100.0,
)

# dataset settings
dataset_type = "NuScenesDataset"
data_root = "data/nuscenes"
ignore_index = -1
names = [
    "barrier",
    "bicycle",
    "bus",
    "car",
    "construction_vehicle",
    "motorcycle",
    "pedestrian",
    "traffic_cone",
    "trailer",
    "truck",
    "driveable_surface",
    "other_flat",
    "sidewalk",
    "terrain",
    "manmade",
    "vegetation",
]

data = dict(
    num_classes=16,
    ignore_index=ignore_index,
    names=names,
    train=dict(
        type=dataset_type,
        split="train",
        data_root=data_root,
        transform=[
            # dict(type="RandomDropout", dropout_ratio=0.2, dropout_application_ratio=0.2),
            # dict(type="RandomRotateTargetAngle", angle=(1/2, 1, 3/2), center=[0, 0, 0], axis='z', p=0.75),
            dict(type="RandomRotate", angle=[-1, 1], axis="z", center=[0, 0, 0], p=0.5),
            # dict(type="RandomRotate", angle=[-1/6, 1/6], axis='x', p=0.5),
            # dict(type="RandomRotate", angle=[-1/6, 1/6], axis='y', p=0.5),
            dict(type="RandomScale", scale=[0.9, 1.1]),
            # dict(type="RandomShift", shift=[0.2, 0.2, 0.2]),
            dict(type="RandomFlip", p=0.5),
            dict(type="RandomJitter", sigma=0.005, clip=0.02),
            # dict(type="ElasticDistortion", distortion_params=[[0.2, 0.4], [0.8, 1.6]]),
            dict(
                type="GridSample",
                grid_size=0.05,
                hash_type="fnv",
                mode="train",
                keys=("coord", "strength", "segment"),
                return_grid_coord=True,
            ),
            # dict(type="SphereCrop", point_max=1000000, mode="random"),
            # dict(type="CenterShift", apply_z=False),
            dict(type="ToTensor"),
            dict(
                type="Collect",
                keys=("coord", "grid_coord", "segment"),
                feat_keys=("coord", "strength"),
            ),
        ],
        test_mode=False,
        ignore_index=ignore_index,
    ),
    val=dict(
        type=dataset_type,
        split="val",
        data_root=data_root,
        transform=[
            # dict(type="PointClip", point_cloud_range=(-51.2, -51.2, -4, 51.2, 51.2, 2.4)),
            dict(
                type="GridSample",
                grid_size=0.05,
                hash_type="fnv",
                mode="train",
                keys=("coord", "strength", "segment"),
                return_grid_coord=True,
            ),
            # dict(type="SphereCrop", point_max=1000000, mode='center'),
            dict(type="ToTensor"),
            dict(
                type="Collect",
                keys=("coord", "grid_coord", "segment"),
                feat_keys=("coord", "strength"),
            ),
        ],
        test_mode=False,
        ignore_index=ignore_index,
    ),
    test=dict(
        type=dataset_type,
        split="val",
        data_root=data_root,
        transform=[
            dict(type="Copy", keys_dict={"segment": "origin_segment"}),
            dict(
                type="GridSample",
                grid_size=0.025,
                hash_type="fnv",
                mode="train",
                keys=("coord", "strength", "segment"),
                return_inverse=True,
            ),
        ],
        test_mode=True,
        test_cfg=dict(
            voxelize=dict(
                type="GridSample",
                grid_size=0.05,
                hash_type="fnv",
                mode="test",
                return_grid_coord=True,
                keys=("coord", "strength"),
            ),
            crop=None,
            post_transform=[
                dict(type="ToTensor"),
                dict(
                    type="Collect",
                    keys=("coord", "grid_coord", "index"),
                    feat_keys=("coord", "strength"),
                ),
            ],
            aug_transform=[
                [dict(type="RandomScale", scale=[0.9, 0.9])],
                [dict(type="RandomScale", scale=[0.95, 0.95])],
                [dict(type="RandomScale", scale=[1, 1])],
                [dict(type="RandomScale", scale=[1.05, 1.05])],
                [dict(type="RandomScale", scale=[1.1, 1.1])],
                [
                    dict(type="RandomScale", scale=[0.9, 0.9]),
                    dict(type="RandomFlip", p=1),
                ],
                [
                    dict(type="RandomScale", scale=[0.95, 0.95]),
                    dict(type="RandomFlip", p=1),
                ],
                [dict(type="RandomScale", scale=[1, 1]), dict(type="RandomFlip", p=1)],
                [
                    dict(type="RandomScale", scale=[1.05, 1.05]),
                    dict(type="RandomFlip", p=1),
                ],
                [
                    dict(type="RandomScale", scale=[1.1, 1.1]),
                    dict(type="RandomFlip", p=1),
                ],
            ],
        ),
        ignore_index=ignore_index,
    ),
)