Initial snapshot: hand motion pipeline (Dyn-HaMR + dex-retargeting + SPIDER)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
+321
@@ -0,0 +1,321 @@
|
||||
model = dict(
|
||||
detector=dict(
|
||||
type='FasterRCNN',
|
||||
backbone=dict(
|
||||
type='ResNet',
|
||||
depth=50,
|
||||
num_stages=4,
|
||||
out_indices=(0, 1, 2, 3),
|
||||
frozen_stages=1,
|
||||
norm_cfg=dict(type='BN', requires_grad=True),
|
||||
norm_eval=True,
|
||||
style='pytorch',
|
||||
init_cfg=dict(
|
||||
type='Pretrained', checkpoint='torchvision://resnet50')),
|
||||
neck=dict(
|
||||
type='FPN',
|
||||
in_channels=[256, 512, 1024, 2048],
|
||||
out_channels=256,
|
||||
num_outs=5),
|
||||
rpn_head=dict(
|
||||
type='RPNHead',
|
||||
in_channels=256,
|
||||
feat_channels=256,
|
||||
anchor_generator=dict(
|
||||
type='AnchorGenerator',
|
||||
scales=[8],
|
||||
ratios=[0.5, 1.0, 2.0],
|
||||
strides=[4, 8, 16, 32, 64]),
|
||||
bbox_coder=dict(
|
||||
type='DeltaXYWHBBoxCoder',
|
||||
target_means=[0.0, 0.0, 0.0, 0.0],
|
||||
target_stds=[1.0, 1.0, 1.0, 1.0],
|
||||
clip_border=False),
|
||||
loss_cls=dict(
|
||||
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
|
||||
loss_bbox=dict(
|
||||
type='SmoothL1Loss', beta=0.1111111111111111,
|
||||
loss_weight=1.0)),
|
||||
roi_head=dict(
|
||||
type='StandardRoIHead',
|
||||
bbox_roi_extractor=dict(
|
||||
type='SingleRoIExtractor',
|
||||
roi_layer=dict(
|
||||
type='RoIAlign', output_size=7, sampling_ratio=0),
|
||||
out_channels=256,
|
||||
featmap_strides=[4, 8, 16, 32]),
|
||||
bbox_head=dict(
|
||||
type='Shared2FCBBoxHead',
|
||||
in_channels=256,
|
||||
fc_out_channels=1024,
|
||||
roi_feat_size=7,
|
||||
num_classes=1,
|
||||
bbox_coder=dict(
|
||||
type='DeltaXYWHBBoxCoder',
|
||||
target_means=[0.0, 0.0, 0.0, 0.0],
|
||||
target_stds=[0.1, 0.1, 0.2, 0.2],
|
||||
clip_border=False),
|
||||
reg_class_agnostic=False,
|
||||
loss_cls=dict(
|
||||
type='CrossEntropyLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=1.0),
|
||||
loss_bbox=dict(type='SmoothL1Loss', loss_weight=1.0))),
|
||||
train_cfg=dict(
|
||||
rpn=dict(
|
||||
assigner=dict(
|
||||
type='MaxIoUAssigner',
|
||||
pos_iou_thr=0.7,
|
||||
neg_iou_thr=0.3,
|
||||
min_pos_iou=0.3,
|
||||
match_low_quality=True,
|
||||
ignore_iof_thr=-1),
|
||||
sampler=dict(
|
||||
type='RandomSampler',
|
||||
num=256,
|
||||
pos_fraction=0.5,
|
||||
neg_pos_ub=-1,
|
||||
add_gt_as_proposals=False),
|
||||
allowed_border=-1,
|
||||
pos_weight=-1,
|
||||
debug=False),
|
||||
rpn_proposal=dict(
|
||||
nms_pre=2000,
|
||||
max_per_img=1000,
|
||||
nms=dict(type='nms', iou_threshold=0.7),
|
||||
min_bbox_size=0),
|
||||
rcnn=dict(
|
||||
assigner=dict(
|
||||
type='MaxIoUAssigner',
|
||||
pos_iou_thr=0.5,
|
||||
neg_iou_thr=0.5,
|
||||
min_pos_iou=0.5,
|
||||
match_low_quality=False,
|
||||
ignore_iof_thr=-1),
|
||||
sampler=dict(
|
||||
type='RandomSampler',
|
||||
num=512,
|
||||
pos_fraction=0.25,
|
||||
neg_pos_ub=-1,
|
||||
add_gt_as_proposals=True),
|
||||
pos_weight=-1,
|
||||
debug=False)),
|
||||
test_cfg=dict(
|
||||
rpn=dict(
|
||||
nms_pre=1000,
|
||||
max_per_img=1000,
|
||||
nms=dict(type='nms', iou_threshold=0.7),
|
||||
min_bbox_size=0),
|
||||
rcnn=dict(
|
||||
score_thr=0.05,
|
||||
nms=dict(type='nms', iou_threshold=0.5),
|
||||
max_per_img=100)),
|
||||
init_cfg=dict(
|
||||
type='Pretrained',
|
||||
checkpoint='https://download.openmmlab.com/mmtracking/'
|
||||
'mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-half-64ee2ed4.pth')),
|
||||
type='DeepSORT',
|
||||
motion=dict(type='KalmanFilter', center_only=False),
|
||||
reid=dict(
|
||||
type='BaseReID',
|
||||
backbone=dict(
|
||||
type='ResNet',
|
||||
depth=50,
|
||||
num_stages=4,
|
||||
out_indices=(3, ),
|
||||
style='pytorch'),
|
||||
neck=dict(type='GlobalAveragePooling', kernel_size=(8, 4), stride=1),
|
||||
head=dict(
|
||||
type='LinearReIDHead',
|
||||
num_fcs=1,
|
||||
in_channels=2048,
|
||||
fc_channels=1024,
|
||||
out_channels=128,
|
||||
num_classes=380,
|
||||
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
|
||||
loss_pairwise=dict(
|
||||
type='TripletLoss', margin=0.3, loss_weight=1.0),
|
||||
norm_cfg=dict(type='BN1d'),
|
||||
act_cfg=dict(type='ReLU')),
|
||||
init_cfg=dict(
|
||||
type='Pretrained',
|
||||
checkpoint='https://download.openmmlab.com/mmtracking/'
|
||||
'mot/reid/tracktor_reid_r50_iter25245-a452f51f.pth')),
|
||||
tracker=dict(
|
||||
type='SortTracker',
|
||||
obj_score_thr=0.5,
|
||||
reid=dict(
|
||||
num_samples=10,
|
||||
img_scale=(256, 128),
|
||||
img_norm_cfg=None,
|
||||
match_score_thr=2.0),
|
||||
match_iou_thr=0.5,
|
||||
momentums=None,
|
||||
num_tentatives=2,
|
||||
num_frames_retain=100))
|
||||
dataset_type = 'MOTChallengeDataset'
|
||||
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='LoadMultiImagesFromFile', to_float32=True),
|
||||
dict(type='SeqLoadAnnotations', with_bbox=True, with_track=True),
|
||||
dict(
|
||||
type='SeqResize',
|
||||
img_scale=(1088, 1088),
|
||||
share_params=True,
|
||||
ratio_range=(0.8, 1.2),
|
||||
keep_ratio=True,
|
||||
bbox_clip_border=False),
|
||||
dict(type='SeqPhotoMetricDistortion', share_params=True),
|
||||
dict(
|
||||
type='SeqRandomCrop',
|
||||
share_params=False,
|
||||
crop_size=(1088, 1088),
|
||||
bbox_clip_border=False),
|
||||
dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
|
||||
dict(
|
||||
type='SeqNormalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='SeqPad', size_divisor=32),
|
||||
dict(type='MatchInstances', skip_nomatch=True),
|
||||
dict(
|
||||
type='VideoCollect',
|
||||
keys=[
|
||||
'img', 'gt_bboxes', 'gt_labels', 'gt_match_indices',
|
||||
'gt_instance_ids'
|
||||
]),
|
||||
dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
|
||||
]
|
||||
test_pipeline = [
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(
|
||||
type='MultiScaleFlipAug',
|
||||
img_scale=(1088, 1088),
|
||||
flip=False,
|
||||
transforms=[
|
||||
dict(type='Resize', keep_ratio=True),
|
||||
dict(type='RandomFlip'),
|
||||
dict(
|
||||
type='Normalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='Pad', size_divisor=32),
|
||||
dict(type='ImageToTensor', keys=['img']),
|
||||
dict(type='VideoCollect', keys=['img'])
|
||||
])
|
||||
]
|
||||
data_root = 'data/MOT17/'
|
||||
data = dict(
|
||||
samples_per_gpu=2,
|
||||
workers_per_gpu=2,
|
||||
train=dict(
|
||||
type='MOTChallengeDataset',
|
||||
visibility_thr=-1,
|
||||
ann_file='data/MOT17/annotations/half-train_cocoformat.json',
|
||||
img_prefix='data/MOT17/train',
|
||||
ref_img_sampler=dict(
|
||||
num_ref_imgs=1,
|
||||
frame_range=10,
|
||||
filter_key_img=True,
|
||||
method='uniform'),
|
||||
pipeline=[
|
||||
dict(type='LoadMultiImagesFromFile', to_float32=True),
|
||||
dict(type='SeqLoadAnnotations', with_bbox=True, with_track=True),
|
||||
dict(
|
||||
type='SeqResize',
|
||||
img_scale=(1088, 1088),
|
||||
share_params=True,
|
||||
ratio_range=(0.8, 1.2),
|
||||
keep_ratio=True,
|
||||
bbox_clip_border=False),
|
||||
dict(type='SeqPhotoMetricDistortion', share_params=True),
|
||||
dict(
|
||||
type='SeqRandomCrop',
|
||||
share_params=False,
|
||||
crop_size=(1088, 1088),
|
||||
bbox_clip_border=False),
|
||||
dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
|
||||
dict(
|
||||
type='SeqNormalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='SeqPad', size_divisor=32),
|
||||
dict(type='MatchInstances', skip_nomatch=True),
|
||||
dict(
|
||||
type='VideoCollect',
|
||||
keys=[
|
||||
'img', 'gt_bboxes', 'gt_labels', 'gt_match_indices',
|
||||
'gt_instance_ids'
|
||||
]),
|
||||
dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
|
||||
]),
|
||||
val=dict(
|
||||
type='MOTChallengeDataset',
|
||||
ann_file='data/MOT17/annotations/half-val_cocoformat.json',
|
||||
img_prefix='data/MOT17/train',
|
||||
ref_img_sampler=None,
|
||||
pipeline=[
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(
|
||||
type='MultiScaleFlipAug',
|
||||
img_scale=(1088, 1088),
|
||||
flip=False,
|
||||
transforms=[
|
||||
dict(type='Resize', keep_ratio=True),
|
||||
dict(type='RandomFlip'),
|
||||
dict(
|
||||
type='Normalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='Pad', size_divisor=32),
|
||||
dict(type='ImageToTensor', keys=['img']),
|
||||
dict(type='VideoCollect', keys=['img'])
|
||||
])
|
||||
]),
|
||||
test=dict(
|
||||
type='MOTChallengeDataset',
|
||||
ann_file='data/MOT17/annotations/half-val_cocoformat.json',
|
||||
img_prefix='data/MOT17/train',
|
||||
ref_img_sampler=None,
|
||||
pipeline=[
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(
|
||||
type='MultiScaleFlipAug',
|
||||
img_scale=(1088, 1088),
|
||||
flip=False,
|
||||
transforms=[
|
||||
dict(type='Resize', keep_ratio=True),
|
||||
dict(type='RandomFlip'),
|
||||
dict(
|
||||
type='Normalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='Pad', size_divisor=32),
|
||||
dict(type='ImageToTensor', keys=['img']),
|
||||
dict(type='VideoCollect', keys=['img'])
|
||||
])
|
||||
]))
|
||||
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
|
||||
optimizer_config = dict(grad_clip=None)
|
||||
checkpoint_config = dict(interval=1)
|
||||
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
|
||||
dist_params = dict(backend='nccl')
|
||||
log_level = 'INFO'
|
||||
load_from = None
|
||||
resume_from = None
|
||||
workflow = [('train', 1)]
|
||||
lr_config = dict(
|
||||
policy='step',
|
||||
warmup='linear',
|
||||
warmup_iters=100,
|
||||
warmup_ratio=0.01,
|
||||
step=[3])
|
||||
total_epochs = 4
|
||||
evaluation = dict(metric=['bbox', 'track'], interval=1)
|
||||
search_metrics = ['MOTA', 'IDF1', 'FN', 'FP', 'IDs', 'MT', 'ML']
|
||||
+325
@@ -0,0 +1,325 @@
|
||||
model = dict(
|
||||
detector=dict(
|
||||
type='FasterRCNN',
|
||||
pretrained='torchvision://resnet50',
|
||||
backbone=dict(
|
||||
type='ResNet',
|
||||
depth=50,
|
||||
num_stages=4,
|
||||
out_indices=(0, 1, 2, 3),
|
||||
frozen_stages=1,
|
||||
norm_cfg=dict(type='BN', requires_grad=True),
|
||||
norm_eval=True,
|
||||
style='pytorch'),
|
||||
neck=dict(
|
||||
type='FPN',
|
||||
in_channels=[256, 512, 1024, 2048],
|
||||
out_channels=256,
|
||||
num_outs=5),
|
||||
rpn_head=dict(
|
||||
type='RPNHead',
|
||||
in_channels=256,
|
||||
feat_channels=256,
|
||||
anchor_generator=dict(
|
||||
type='AnchorGenerator',
|
||||
scales=[8],
|
||||
ratios=[0.5, 1.0, 2.0],
|
||||
strides=[4, 8, 16, 32, 64]),
|
||||
bbox_coder=dict(
|
||||
type='DeltaXYWHBBoxCoder',
|
||||
target_means=[0.0, 0.0, 0.0, 0.0],
|
||||
target_stds=[1.0, 1.0, 1.0, 1.0],
|
||||
clip_border=False),
|
||||
loss_cls=dict(
|
||||
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
|
||||
loss_bbox=dict(
|
||||
type='SmoothL1Loss', beta=0.1111111111111111,
|
||||
loss_weight=1.0)),
|
||||
roi_head=dict(
|
||||
type='StandardRoIHead',
|
||||
bbox_roi_extractor=dict(
|
||||
type='SingleRoIExtractor',
|
||||
roi_layer=dict(
|
||||
type='RoIAlign', output_size=7, sampling_ratio=0),
|
||||
out_channels=256,
|
||||
featmap_strides=[4, 8, 16, 32]),
|
||||
bbox_head=dict(
|
||||
type='Shared2FCBBoxHead',
|
||||
in_channels=256,
|
||||
fc_out_channels=1024,
|
||||
roi_feat_size=7,
|
||||
num_classes=1,
|
||||
bbox_coder=dict(
|
||||
type='DeltaXYWHBBoxCoder',
|
||||
target_means=[0.0, 0.0, 0.0, 0.0],
|
||||
target_stds=[0.1, 0.1, 0.2, 0.2],
|
||||
clip_border=False),
|
||||
reg_class_agnostic=False,
|
||||
loss_cls=dict(
|
||||
type='CrossEntropyLoss',
|
||||
use_sigmoid=False,
|
||||
loss_weight=1.0),
|
||||
loss_bbox=dict(type='SmoothL1Loss', loss_weight=1.0))),
|
||||
train_cfg=dict(
|
||||
rpn=dict(
|
||||
assigner=dict(
|
||||
type='MaxIoUAssigner',
|
||||
pos_iou_thr=0.7,
|
||||
neg_iou_thr=0.3,
|
||||
min_pos_iou=0.3,
|
||||
match_low_quality=True,
|
||||
ignore_iof_thr=-1),
|
||||
sampler=dict(
|
||||
type='RandomSampler',
|
||||
num=256,
|
||||
pos_fraction=0.5,
|
||||
neg_pos_ub=-1,
|
||||
add_gt_as_proposals=False),
|
||||
allowed_border=-1,
|
||||
pos_weight=-1,
|
||||
debug=False),
|
||||
rpn_proposal=dict(
|
||||
nms_pre=2000,
|
||||
max_per_img=1000,
|
||||
nms=dict(type='nms', iou_threshold=0.7),
|
||||
min_bbox_size=0),
|
||||
rcnn=dict(
|
||||
assigner=dict(
|
||||
type='MaxIoUAssigner',
|
||||
pos_iou_thr=0.5,
|
||||
neg_iou_thr=0.5,
|
||||
min_pos_iou=0.5,
|
||||
match_low_quality=False,
|
||||
ignore_iof_thr=-1),
|
||||
sampler=dict(
|
||||
type='RandomSampler',
|
||||
num=512,
|
||||
pos_fraction=0.25,
|
||||
neg_pos_ub=-1,
|
||||
add_gt_as_proposals=True),
|
||||
pos_weight=-1,
|
||||
debug=False)),
|
||||
test_cfg=dict(
|
||||
rpn=dict(
|
||||
nms_pre=1000,
|
||||
max_per_img=1000,
|
||||
nms=dict(type='nms', iou_threshold=0.7),
|
||||
min_bbox_size=0),
|
||||
rcnn=dict(
|
||||
score_thr=0.05,
|
||||
nms=dict(type='nms', iou_threshold=0.5),
|
||||
max_per_img=100))),
|
||||
type='Tracktor',
|
||||
pretrains=dict(
|
||||
detector='https://download.openmmlab.com/mmtracking/'
|
||||
'mot/faster_rcnn/faster-rcnn_r50_fpn_4e_mot17-ffa52ae7.pth',
|
||||
reid='https://download.openmmlab.com/mmtracking/mot/'
|
||||
'reid/reid_r50_6e_mot17-4bf6b63d.pth'),
|
||||
reid=dict(
|
||||
type='BaseReID',
|
||||
backbone=dict(
|
||||
type='ResNet',
|
||||
depth=50,
|
||||
num_stages=4,
|
||||
out_indices=(3, ),
|
||||
style='pytorch'),
|
||||
neck=dict(type='GlobalAveragePooling', kernel_size=(8, 4), stride=1),
|
||||
head=dict(
|
||||
type='LinearReIDHead',
|
||||
num_fcs=1,
|
||||
in_channels=2048,
|
||||
fc_channels=1024,
|
||||
out_channels=128,
|
||||
num_classes=378,
|
||||
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
|
||||
loss_pairwise=dict(
|
||||
type='TripletLoss', margin=0.3, loss_weight=1.0),
|
||||
norm_cfg=dict(type='BN1d'),
|
||||
act_cfg=dict(type='ReLU'))),
|
||||
motion=dict(
|
||||
type='CameraMotionCompensation',
|
||||
warp_mode='cv2.MOTION_EUCLIDEAN',
|
||||
num_iters=100,
|
||||
stop_eps=1e-05),
|
||||
tracker=dict(
|
||||
type='TracktorTracker',
|
||||
obj_score_thr=0.5,
|
||||
regression=dict(
|
||||
obj_score_thr=0.5,
|
||||
nms=dict(type='nms', iou_threshold=0.6),
|
||||
match_iou_thr=0.3),
|
||||
reid=dict(
|
||||
num_samples=10,
|
||||
img_scale=(256, 128),
|
||||
img_norm_cfg=None,
|
||||
match_score_thr=2.0,
|
||||
match_iou_thr=0.2),
|
||||
momentums=None,
|
||||
num_frames_retain=10))
|
||||
dataset_type = 'MOTChallengeDataset'
|
||||
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='LoadMultiImagesFromFile', to_float32=True),
|
||||
dict(type='SeqLoadAnnotations', with_bbox=True, with_track=True),
|
||||
dict(
|
||||
type='SeqResize',
|
||||
img_scale=(1088, 1088),
|
||||
share_params=True,
|
||||
ratio_range=(0.8, 1.2),
|
||||
keep_ratio=True,
|
||||
bbox_clip_border=False),
|
||||
dict(type='SeqPhotoMetricDistortion', share_params=True),
|
||||
dict(
|
||||
type='SeqRandomCrop',
|
||||
share_params=False,
|
||||
crop_size=(1088, 1088),
|
||||
bbox_clip_border=False),
|
||||
dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
|
||||
dict(
|
||||
type='SeqNormalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='SeqPad', size_divisor=32),
|
||||
dict(type='MatchInstances', skip_nomatch=True),
|
||||
dict(
|
||||
type='VideoCollect',
|
||||
keys=[
|
||||
'img', 'gt_bboxes', 'gt_labels', 'gt_match_indices',
|
||||
'gt_instance_ids'
|
||||
]),
|
||||
dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
|
||||
]
|
||||
test_pipeline = [
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(
|
||||
type='MultiScaleFlipAug',
|
||||
img_scale=(1088, 1088),
|
||||
flip=False,
|
||||
transforms=[
|
||||
dict(type='Resize', keep_ratio=True),
|
||||
dict(type='RandomFlip'),
|
||||
dict(
|
||||
type='Normalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='Pad', size_divisor=32),
|
||||
dict(type='ImageToTensor', keys=['img']),
|
||||
dict(type='VideoCollect', keys=['img'])
|
||||
])
|
||||
]
|
||||
data_root = 'data/MOT17/'
|
||||
data = dict(
|
||||
samples_per_gpu=2,
|
||||
workers_per_gpu=2,
|
||||
train=dict(
|
||||
type='MOTChallengeDataset',
|
||||
visibility_thr=-1,
|
||||
ann_file='data/MOT17/annotations/train_cocoformat.json',
|
||||
img_prefix='data/MOT17/train',
|
||||
ref_img_sampler=dict(
|
||||
num_ref_imgs=1,
|
||||
frame_range=10,
|
||||
filter_key_img=True,
|
||||
method='uniform'),
|
||||
pipeline=[
|
||||
dict(type='LoadMultiImagesFromFile', to_float32=True),
|
||||
dict(type='SeqLoadAnnotations', with_bbox=True, with_track=True),
|
||||
dict(
|
||||
type='SeqResize',
|
||||
img_scale=(1088, 1088),
|
||||
share_params=True,
|
||||
ratio_range=(0.8, 1.2),
|
||||
keep_ratio=True,
|
||||
bbox_clip_border=False),
|
||||
dict(type='SeqPhotoMetricDistortion', share_params=True),
|
||||
dict(
|
||||
type='SeqRandomCrop',
|
||||
share_params=False,
|
||||
crop_size=(1088, 1088),
|
||||
bbox_clip_border=False),
|
||||
dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5),
|
||||
dict(
|
||||
type='SeqNormalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='SeqPad', size_divisor=32),
|
||||
dict(type='MatchInstances', skip_nomatch=True),
|
||||
dict(
|
||||
type='VideoCollect',
|
||||
keys=[
|
||||
'img', 'gt_bboxes', 'gt_labels', 'gt_match_indices',
|
||||
'gt_instance_ids'
|
||||
]),
|
||||
dict(type='SeqDefaultFormatBundle', ref_prefix='ref')
|
||||
]),
|
||||
val=dict(
|
||||
type='MOTChallengeDataset',
|
||||
ann_file='data/MOT17/annotations/train_cocoformat.json',
|
||||
img_prefix='data/MOT17/train',
|
||||
ref_img_sampler=None,
|
||||
pipeline=[
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(
|
||||
type='MultiScaleFlipAug',
|
||||
img_scale=(1088, 1088),
|
||||
flip=False,
|
||||
transforms=[
|
||||
dict(type='Resize', keep_ratio=True),
|
||||
dict(type='RandomFlip'),
|
||||
dict(
|
||||
type='Normalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='Pad', size_divisor=32),
|
||||
dict(type='ImageToTensor', keys=['img']),
|
||||
dict(type='VideoCollect', keys=['img'])
|
||||
])
|
||||
]),
|
||||
test=dict(
|
||||
type='MOTChallengeDataset',
|
||||
ann_file='data/MOT17/annotations/train_cocoformat.json',
|
||||
img_prefix='data/MOT17/train',
|
||||
ref_img_sampler=None,
|
||||
pipeline=[
|
||||
dict(type='LoadImageFromFile'),
|
||||
dict(
|
||||
type='MultiScaleFlipAug',
|
||||
img_scale=(1088, 1088),
|
||||
flip=False,
|
||||
transforms=[
|
||||
dict(type='Resize', keep_ratio=True),
|
||||
dict(type='RandomFlip'),
|
||||
dict(
|
||||
type='Normalize',
|
||||
mean=[123.675, 116.28, 103.53],
|
||||
std=[58.395, 57.12, 57.375],
|
||||
to_rgb=True),
|
||||
dict(type='Pad', size_divisor=32),
|
||||
dict(type='ImageToTensor', keys=['img']),
|
||||
dict(type='VideoCollect', keys=['img'])
|
||||
])
|
||||
]))
|
||||
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
|
||||
optimizer_config = dict(grad_clip=None)
|
||||
checkpoint_config = dict(interval=1)
|
||||
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
|
||||
dist_params = dict(backend='nccl')
|
||||
log_level = 'INFO'
|
||||
load_from = None
|
||||
resume_from = None
|
||||
workflow = [('train', 1)]
|
||||
lr_config = dict(
|
||||
policy='step',
|
||||
warmup='linear',
|
||||
warmup_iters=100,
|
||||
warmup_ratio=0.01,
|
||||
step=[3])
|
||||
total_epochs = 4
|
||||
evaluation = dict(metric=['bbox', 'track'], interval=1)
|
||||
search_metrics = ['MOTA', 'IDF1', 'FN', 'FP', 'IDs', 'MT', 'ML']
|
||||
test_set = 'train'
|
||||
Reference in New Issue
Block a user