configs/det/cascade_rcnn_swin-t_fpn_3x_det_bdd100k.py

"""Cascade RCNN with Swin-T, 3x schedule, MS training."""

_base_ = [
    "../_base_/models/cascade_rcnn_r50_fpn.py",
    "../_base_/datasets/bdd100k_mstrain.py",
    "../_base_/schedules/schedule_3x.py",
    "../_base_/default_runtime.py",
]

pretrained = "https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth"  # noqa
model = dict(
    backbone=dict(
        _delete_=True,
        type="SwinTransformer",
        embed_dims=96,
        depths=[2, 2, 6, 2],
        num_heads=[3, 6, 12, 24],
        window_size=7,
        mlp_ratio=4,
        qkv_bias=True,
        qk_scale=None,
        drop_rate=0.0,
        attn_drop_rate=0.0,
        drop_path_rate=0.2,
        patch_norm=True,
        out_indices=(0, 1, 2, 3),
        with_cp=False,
        convert_weights=True,
        init_cfg=dict(type="Pretrained", checkpoint=pretrained),
    ),
    neck=dict(in_channels=[96, 192, 384, 768]),
)

optimizer = dict(
    _delete_=True,
    type="AdamW",
    lr=0.0001,
    betas=(0.9, 0.999),
    weight_decay=0.05,
    paramwise_cfg=dict(
        custom_keys={
            "absolute_pos_embed": dict(decay_mult=0.0),
            "relative_position_bias_table": dict(decay_mult=0.0),
            "norm": dict(decay_mult=0.0),
        }
    ),
)
lr_config = dict(warmup_iters=1000, step=[27, 33])

data = dict(samples_per_gpu=2, workers_per_gpu=2)
load_from = "https://dl.cv.ethz.ch/bdd100k/det/models/cascade_rcnn_swin-t_fpn_3x_det_bdd100k.pth"