Spaces:
Runtime error
Runtime error
File size: 6,999 Bytes
f1dd031 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 |
_base_ = [
'../../projects/grounding_dino/grounding_dino_swin-b_pretrain_mixeddata_masa.py',
'../default_runtime.py'
]
default_scope = 'mmdet'
detector = _base_.model
detector.pop('data_preprocessor')
detector['init_cfg'] = dict(
type='Pretrained',
checkpoint= 'saved_models/tsa_models/groundingdino_swinb_cogcoor_mmdet-55949c9c.pth'
# noqa: E501
)
detector['type'] = 'GroundingDINOMasa'
del _base_.model
model = dict(
type='MASA',
freeze_detector=True,
unified_backbone=True,
load_public_dets = False,
given_dets = True,
data_preprocessor=dict(
type='TrackDataPreprocessor',
# Image normalization parameters
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
# Image padding parameters
pad_mask=False, # In instance segmentation, the mask needs to be padded
pad_size_divisor=32), # Padding the image to multiples of 32
detector=detector,
masa_adapter=[
dict(
type='FPN',
in_channels=[256, 512, 1024],
out_channels=256,
norm_cfg=dict(type='SyncBN', requires_grad=True),
num_outs=5),
dict(
type='DeformFusion',
in_channels=256,
out_channels=256,
num_blocks=3)],
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=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, 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=[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.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
# model training and testing settings
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=0.02,
# nms=dict(type='nms', iou_threshold=0.5),
nms=dict(type='nms',
iou_threshold=0.5,
class_agnostic=True,
split_thr=100000),
max_per_img=50,
mask_thr_binary=0.5)
# soft-nms is also supported for rcnn testing
# e.g., nms=dict(type='soft_nms', iou_threshold=0.5, min_score=0.05)
),
track_head=dict(
type='MasaTrackHead',
roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[8, 16, 32]),
embed_head=dict(
type='QuasiDenseEmbedHead',
num_convs=4,
num_fcs=1,
embed_channels=256,
norm_cfg=dict(type='GN', num_groups=32),
loss_track=dict(type='UnbiasedContrastLoss', loss_weight=0.25),
loss_track_aux=dict(
type='MarginL2Loss',
neg_pos_ub=3,
pos_margin=0,
neg_margin=0.1,
hard_mining=True,
loss_weight=1.0)),
train_cfg=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='CombinedSampler',
num=512,
pos_fraction=0.5,
neg_pos_ub=3,
add_gt_as_proposals=True,
pos_sampler=dict(type='InstanceBalancedPosSampler'),
neg_sampler=dict(type='RandomSampler')))),
tracker=dict(
type='MasaTaoTracker',
init_score_thr=0.1,
obj_score_thr=0.01,
match_score_thr=0.5,
memo_tracklet_frames=10,
memo_momentum=0.8,
with_cats=False,
max_distance=100,
fps=30,
)
)
inference_pipeline = [
dict(
type='TransformBroadcaster',
transforms=[
dict(
type='Resize',
scale=(1333, 800),
keep_ratio=True),
]),
dict(type='PackTrackInputs')
]
# runtime settings
train_cfg = None
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
default_hooks = dict(
logger=dict(type='LoggerHook', interval=50),
visualization=dict(type='TrackVisualizationHook', draw=False),
checkpoint = dict(type='CheckpointHook', interval=1),
)
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
type='MasaTrackLocalVisualizer', vis_backends=vis_backends, name='visualizer')
|