|
"""Dataset settings."""
|
|
|
|
dataset_type = "BDD100KDetDataset"
|
|
data_root = "../data/bdd100k/"
|
|
img_norm_cfg = dict(
|
|
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True
|
|
)
|
|
train_pipeline = [
|
|
dict(type="LoadImageFromFile"),
|
|
dict(type="LoadAnnotations", with_bbox=True),
|
|
dict(
|
|
type="Resize",
|
|
img_scale=[
|
|
(1280, 600),
|
|
(1280, 624),
|
|
(1280, 648),
|
|
(1280, 672),
|
|
(1280, 696),
|
|
(1280, 720),
|
|
],
|
|
multiscale_mode="value",
|
|
keep_ratio=True,
|
|
),
|
|
dict(type="RandomFlip", flip_ratio=0.5),
|
|
dict(type="Normalize", **img_norm_cfg),
|
|
dict(type="Pad", size_divisor=32),
|
|
dict(type="DefaultFormatBundle"),
|
|
dict(type="Collect", keys=["img", "gt_bboxes", "gt_labels"]),
|
|
]
|
|
test_pipeline = [
|
|
dict(type="LoadImageFromFile"),
|
|
dict(
|
|
type="MultiScaleFlipAug",
|
|
img_scale=(1280, 720),
|
|
flip=False,
|
|
transforms=[
|
|
dict(type="Resize", keep_ratio=True),
|
|
dict(type="RandomFlip"),
|
|
dict(type="Normalize", **img_norm_cfg),
|
|
dict(type="Pad", size_divisor=32),
|
|
dict(type="ImageToTensor", keys=["img"]),
|
|
dict(type="Collect", keys=["img"]),
|
|
],
|
|
),
|
|
]
|
|
data = dict(
|
|
samples_per_gpu=4,
|
|
workers_per_gpu=4,
|
|
train=dict(
|
|
type=dataset_type,
|
|
ann_file=data_root + "jsons/det_train_cocofmt.json",
|
|
img_prefix=data_root + "images/100k/train",
|
|
pipeline=train_pipeline,
|
|
),
|
|
val=dict(
|
|
type=dataset_type,
|
|
ann_file=data_root + "jsons/det_val_cocofmt.json",
|
|
img_prefix=data_root + "images/100k/val",
|
|
pipeline=test_pipeline,
|
|
),
|
|
test=dict(
|
|
type=dataset_type,
|
|
ann_file=data_root + "jsons/det_val_cocofmt.json",
|
|
img_prefix=data_root + "images/100k/val",
|
|
pipeline=test_pipeline,
|
|
),
|
|
)
|
|
evaluation = dict(interval=1, metric="bbox")
|
|
|
