mmpose/demo/mmdetection_cfg/ssdlite_mobilenetv2_scratch...

154 lines
4.8 KiB
Python

# =========================================================
# from 'mmdetection/configs/_base_/default_runtime.py'
# =========================================================
default_scope = 'mmdet'
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
custom_hooks = [dict(type='NumClassCheckHook')]
# =========================================================
# model settings
data_preprocessor = dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_size_divisor=1)
model = dict(
type='SingleStageDetector',
data_preprocessor=data_preprocessor,
backbone=dict(
type='MobileNetV2',
out_indices=(4, 7),
norm_cfg=dict(type='BN', eps=0.001, momentum=0.03),
init_cfg=dict(type='TruncNormal', layer='Conv2d', std=0.03)),
neck=dict(
type='SSDNeck',
in_channels=(96, 1280),
out_channels=(96, 1280, 512, 256, 256, 128),
level_strides=(2, 2, 2, 2),
level_paddings=(1, 1, 1, 1),
l2_norm_scale=None,
use_depthwise=True,
norm_cfg=dict(type='BN', eps=0.001, momentum=0.03),
act_cfg=dict(type='ReLU6'),
init_cfg=dict(type='TruncNormal', layer='Conv2d', std=0.03)),
bbox_head=dict(
type='SSDHead',
in_channels=(96, 1280, 512, 256, 256, 128),
num_classes=1,
use_depthwise=True,
norm_cfg=dict(type='BN', eps=0.001, momentum=0.03),
act_cfg=dict(type='ReLU6'),
init_cfg=dict(type='Normal', layer='Conv2d', std=0.001),
# set anchor size manually instead of using the predefined
# SSD300 setting.
anchor_generator=dict(
type='SSDAnchorGenerator',
scale_major=False,
strides=[16, 32, 64, 107, 160, 320],
ratios=[[2, 3], [2, 3], [2, 3], [2, 3], [2, 3], [2, 3]],
min_sizes=[48, 100, 150, 202, 253, 304],
max_sizes=[100, 150, 202, 253, 304, 320]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[0.1, 0.1, 0.2, 0.2])),
# model training and testing settings
train_cfg=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.,
ignore_iof_thr=-1,
gt_max_assign_all=False),
sampler=dict(type='PseudoSampler'),
smoothl1_beta=1.,
allowed_border=-1,
pos_weight=-1,
neg_pos_ratio=3,
debug=False),
test_cfg=dict(
nms_pre=1000,
nms=dict(type='nms', iou_threshold=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200))
cudnn_benchmark = True
# dataset settings
file_client_args = dict(backend='disk')
dataset_type = 'CocoDataset'
data_root = 'data/onehand10k/'
classes = ('hand', )
input_size = 320
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(input_size, input_size), keep_ratio=False),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
val_dataloader = dict(
batch_size=8,
num_workers=2,
persistent_workers=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/onehand10k_test.json',
test_mode=True,
pipeline=test_pipeline))
test_dataloader = val_dataloader
# optimizer
optimizer = dict(type='SGD', lr=0.015, momentum=0.9, weight_decay=4.0e-5)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='CosineAnnealing',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
min_lr=0)
runner = dict(type='EpochBasedRunner', max_epochs=120)
# Avoid evaluation and saving weights too frequently
evaluation = dict(interval=5, metric='bbox')
checkpoint_config = dict(interval=5)
custom_hooks = [
dict(type='NumClassCheckHook'),
dict(type='CheckInvalidLossHook', interval=50, priority='VERY_LOW')
]
log_config = dict(interval=5)
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (24 samples per GPU)
auto_scale_lr = dict(base_batch_size=192)
load_from = 'https://download.openmmlab.com/mmdetection/'
'v2.0/ssd/ssdlite_mobilenetv2_scratch_600e_coco/'
'ssdlite_mobilenetv2_scratch_600e_coco_20210629_110627-974d9307.pth'
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
type='DetLocalVisualizer', vis_backends=vis_backends, name='visualizer')