|
|
"""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" |
|
|
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" |
|
|
|
