submodules/PointTransformerV3/Pointcept/configs/structured3d/semseg-pt-v2m2-0-base.py

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

# misc custom setting
batch_size = 12  # bs: total bs in all gpus
mix_prob = 0.8
empty_cache = False
enable_amp = True

# model settings
model = dict(
    type="DefaultSegmentor",
    backbone=dict(
        type="PT-v2m2",
        in_channels=9,
        num_classes=25,
        patch_embed_depth=1,
        patch_embed_channels=48,
        patch_embed_groups=6,
        patch_embed_neighbours=8,
        enc_depths=(2, 2, 6, 2),
        enc_channels=(96, 192, 384, 512),
        enc_groups=(12, 24, 48, 64),
        enc_neighbours=(16, 16, 16, 16),
        dec_depths=(1, 1, 1, 1),
        dec_channels=(48, 96, 192, 384),
        dec_groups=(6, 12, 24, 48),
        dec_neighbours=(16, 16, 16, 16),
        grid_sizes=(0.06, 0.15, 0.375, 0.9375),  # x3, x2.5, x2.5, x2.5
        attn_qkv_bias=True,
        pe_multiplier=False,
        pe_bias=True,
        attn_drop_rate=0.0,
        drop_path_rate=0.3,
        enable_checkpoint=False,
        unpool_backend="map",  # map / interp
    ),
    criteria=[dict(type="CrossEntropyLoss", loss_weight=1.0, ignore_index=-1)],
)

# scheduler settings
epoch = 100
optimizer = dict(type="SGD", lr=0.05, momentum=0.9, weight_decay=0.0001, nesterov=True)
scheduler = dict(
    type="OneCycleLR",
    max_lr=optimizer["lr"],
    pct_start=0.05,
    anneal_strategy="cos",
    div_factor=10.0,
    final_div_factor=10000.0,
)

# dataset settings
dataset_type = "Structured3DDataset"
data_root = "data/structured3d"

data = dict(
    num_classes=25,
    ignore_index=-1,
    names=(
        "wall",
        "floor",
        "cabinet",
        "bed",
        "chair",
        "sofa",
        "table",
        "door",
        "window",
        "picture",
        "desk",
        "shelves",
        "curtain",
        "dresser",
        "pillow",
        "mirror",
        "ceiling",
        "refrigerator",
        "television",
        "nightstand",
        "sink",
        "lamp",
        "otherstructure",
        "otherfurniture",
        "otherprop",
    ),
    train=dict(
        type=dataset_type,
        split="train",
        data_root=data_root,
        transform=[
            dict(type="CenterShift", apply_z=True),
            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 / 64, 1 / 64], axis="x", p=0.5),
            dict(type="RandomRotate", angle=[-1 / 64, 1 / 64], 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="ChromaticAutoContrast", p=0.2, blend_factor=None),
            dict(type="ChromaticTranslation", p=0.95, ratio=0.05),
            dict(type="ChromaticJitter", p=0.95, std=0.05),
            # dict(type="HueSaturationTranslation", hue_max=0.2, saturation_max=0.2),
            # dict(type="RandomColorDrop", p=0.2, color_augment=0.0),
            dict(
                type="GridSample",
                grid_size=0.02,
                hash_type="fnv",
                mode="train",
                return_grid_coord=True,
            ),
            dict(type="SphereCrop", sample_rate=0.8, mode="random"),
            dict(type="SphereCrop", point_max=120000, mode="random"),
            dict(type="CenterShift", apply_z=False),
            dict(type="NormalizeColor"),
            dict(type="ShufflePoint"),
            dict(type="ToTensor"),
            dict(
                type="Collect",
                keys=("coord", "grid_coord", "segment"),
                feat_keys=("coord", "color", "normal"),
            ),
        ],
        test_mode=False,
    ),
    val=dict(
        type=dataset_type,
        split="val",
        data_root=data_root,
        transform=[
            dict(type="CenterShift", apply_z=True),
            dict(
                type="GridSample",
                grid_size=0.02,
                hash_type="fnv",
                mode="train",
                return_grid_coord=True,
            ),
            # dict(type="SphereCrop", point_max=1000000, mode="center"),
            dict(type="CenterShift", apply_z=False),
            dict(type="NormalizeColor"),
            dict(type="ToTensor"),
            dict(
                type="Collect",
                keys=("coord", "grid_coord", "segment"),
                feat_keys=("coord", "color", "normal"),
            ),
        ],
        test_mode=False,
    ),
    test=dict(
        type=dataset_type,
        split="val",
        data_root=data_root,
        transform=[
            dict(type="CenterShift", apply_z=True),
            dict(type="NormalizeColor"),
        ],
        test_mode=True,
        test_cfg=dict(
            voxelize=dict(
                type="GridSample",
                grid_size=0.02,
                hash_type="fnv",
                mode="test",
                return_grid_coord=True,
                keys=("coord", "color", "normal"),
            ),
            crop=None,
            post_transform=[
                dict(type="CenterShift", apply_z=False),
                dict(type="ToTensor"),
                dict(
                    type="Collect",
                    keys=("coord", "grid_coord", "index"),
                    feat_keys=("coord", "color", "normal"),
                ),
            ],
            aug_transform=[
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[0],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    )
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[1 / 2],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    )
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[1],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    )
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[3 / 2],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    )
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[0],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    ),
                    dict(type="RandomScale", scale=[0.95, 0.95]),
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[1 / 2],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    ),
                    dict(type="RandomScale", scale=[0.95, 0.95]),
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[1],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    ),
                    dict(type="RandomScale", scale=[0.95, 0.95]),
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[3 / 2],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    ),
                    dict(type="RandomScale", scale=[0.95, 0.95]),
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[0],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    ),
                    dict(type="RandomScale", scale=[1.05, 1.05]),
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[1 / 2],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    ),
                    dict(type="RandomScale", scale=[1.05, 1.05]),
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[1],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    ),
                    dict(type="RandomScale", scale=[1.05, 1.05]),
                ],
                [
                    dict(
                        type="RandomRotateTargetAngle",
                        angle=[3 / 2],
                        axis="z",
                        center=[0, 0, 0],
                        p=1,
                    ),
                    dict(type="RandomScale", scale=[1.05, 1.05]),
                ],
                [dict(type="RandomFlip", p=1)],
            ],
        ),
    ),
)