110 lines
3.4 KiB
Python
110 lines
3.4 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
model = dict(
|
|
type='YOLOV3',
|
|
backbone=dict(
|
|
type='MobileNetV2',
|
|
out_indices=(2, 4, 6),
|
|
act_cfg=dict(type='LeakyReLU', negative_slope=0.1),
|
|
init_cfg=dict(
|
|
type='Pretrained', checkpoint='open-mmlab://mmdet/mobilenet_v2')),
|
|
neck=dict(
|
|
type='YOLOV3Neck',
|
|
num_scales=3,
|
|
in_channels=[320, 96, 32],
|
|
out_channels=[96, 96, 96]),
|
|
bbox_head=dict(
|
|
type='YOLOV3Head',
|
|
num_classes=80,
|
|
in_channels=[96, 96, 96],
|
|
out_channels=[96, 96, 96],
|
|
anchor_generator=dict(
|
|
type='YOLOAnchorGenerator',
|
|
base_sizes=[[(116, 90), (156, 198), (373, 326)],
|
|
[(30, 61), (62, 45), (59, 119)],
|
|
[(10, 13), (16, 30), (33, 23)]],
|
|
strides=[32, 16, 8]),
|
|
bbox_coder=dict(type='YOLOBBoxCoder'),
|
|
featmap_strides=[32, 16, 8],
|
|
loss_cls=dict(
|
|
type='CrossEntropyLoss',
|
|
use_sigmoid=True,
|
|
loss_weight=1.0,
|
|
reduction='sum'),
|
|
loss_conf=dict(
|
|
type='CrossEntropyLoss',
|
|
use_sigmoid=True,
|
|
loss_weight=1.0,
|
|
reduction='sum'),
|
|
loss_xy=dict(
|
|
type='CrossEntropyLoss',
|
|
use_sigmoid=True,
|
|
loss_weight=2.0,
|
|
reduction='sum'),
|
|
loss_wh=dict(type='MSELoss', loss_weight=2.0, reduction='sum')),
|
|
# training and testing settings
|
|
train_cfg=dict(
|
|
assigner=dict(
|
|
type='GridAssigner',
|
|
pos_iou_thr=0.5,
|
|
neg_iou_thr=0.5,
|
|
min_pos_iou=0)),
|
|
test_cfg=dict(
|
|
nms_pre=1000,
|
|
min_bbox_size=0,
|
|
score_thr=0.05,
|
|
conf_thr=0.005,
|
|
nms=dict(type='nms', iou_threshold=0.45),
|
|
max_per_img=100))
|
|
# dataset settings
|
|
dataset_type = 'CocoDataset'
|
|
data_root = '.'
|
|
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', to_float32=True),
|
|
dict(type='LoadAnnotations', with_bbox=True),
|
|
dict(type='PhotoMetricDistortion'),
|
|
dict(
|
|
type='Expand',
|
|
mean=img_norm_cfg['mean'],
|
|
to_rgb=img_norm_cfg['to_rgb'],
|
|
ratio_range=(1, 2)),
|
|
dict(
|
|
type='MinIoURandomCrop',
|
|
min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
|
|
min_crop_size=0.3),
|
|
dict(
|
|
type='Resize',
|
|
img_scale=[(320, 320), (416, 416)],
|
|
multiscale_mode='range',
|
|
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=(416, 416),
|
|
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='DefaultFormatBundle'),
|
|
dict(type='Collect', keys=['img'])
|
|
])
|
|
]
|
|
data = dict(
|
|
samples_per_gpu=24,
|
|
workers_per_gpu=4,
|
|
test=dict(
|
|
type=dataset_type,
|
|
ann_file='tests/test_codebase/test_mmdet/data/coco_sample.json',
|
|
img_prefix=data_root,
|
|
pipeline=test_pipeline))
|