Spaces:
Build error
Build error
File size: 5,776 Bytes
c7f0cc1 |
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 |
_base_ = [
'../_base_/models/detr4seg_r101.py', '../_base_/datasets/psg.py',
'../_base_/custom_runtime.py'
]
custom_imports = dict(imports=[
'openpsg.models.frameworks.detr4seg',
'openpsg.models.relation_heads.detr4seg_head', 'openpsg.datasets',
'openpsg.datasets.pipelines.loading',
'openpsg.datasets.pipelines.rel_randomcrop',
'openpsg.models.relation_heads.approaches.matcher',
'openpsg.models.losses.seg_losses'
],
allow_failed_imports=False)
object_classes = [
'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train',
'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign',
'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag',
'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite',
'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon',
'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant',
'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
'hair drier', 'toothbrush', 'banner', 'blanket', 'bridge', 'cardboard',
'counter', 'curtain', 'door-stuff', 'floor-wood', 'flower', 'fruit',
'gravel', 'house', 'light', 'mirror-stuff', 'net', 'pillow', 'platform',
'playingfield', 'railroad', 'river', 'road', 'roof', 'sand', 'sea',
'shelf', 'snow', 'stairs', 'tent', 'towel', 'wall-brick', 'wall-stone',
'wall-tile', 'wall-wood', 'water-other', 'window-blind', 'window-other',
'tree-merged', 'fence-merged', 'ceiling-merged', 'sky-other-merged',
'cabinet-merged', 'table-merged', 'floor-other-merged', 'pavement-merged',
'mountain-merged', 'grass-merged', 'dirt-merged', 'paper-merged',
'food-other-merged', 'building-other-merged', 'rock-merged',
'wall-other-merged', 'rug-merged'
]
model = dict(bbox_head=dict(
num_classes=len(object_classes),
object_classes=object_classes,
))
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True)
# train_pipeline, NOTE the img_scale and the Pad's size_divisor is different
# from the default setting in mmdet.
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadSceneGraphAnnotations', with_bbox=True, with_rel=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='AutoAugment',
policies=[
[
dict(type='Resize',
img_scale=[(480, 1333), (512, 1333), (544, 1333),
(576, 1333), (608, 1333), (640, 1333),
(672, 1333), (704, 1333), (736, 1333),
(768, 1333), (800, 1333)],
multiscale_mode='value',
keep_ratio=True)
],
[
dict(type='Resize',
img_scale=[(400, 1333), (500, 1333), (600, 1333)],
multiscale_mode='value',
keep_ratio=True),
dict(type='RandomCrop',
crop_type='absolute_range',
crop_size=(384, 600),
allow_negative_crop=False), # no empty relations
dict(type='Resize',
img_scale=[(480, 1333), (512, 1333), (544, 1333),
(576, 1333), (608, 1333), (640, 1333),
(672, 1333), (704, 1333), (736, 1333),
(768, 1333), (800, 1333)],
multiscale_mode='value',
override=True,
keep_ratio=True)
]
]),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=1),
dict(type='RelsFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
# test_pipeline, NOTE the Pad's size_divisor is different from the default
# setting (size_divisor=32). While there is little effect on the performance
# whether we use the default setting or use size_divisor=1.
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=1),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(samples_per_gpu=2,
workers_per_gpu=2,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(
type='AdamW',
lr=0.0001,
weight_decay=0.0001,
paramwise_cfg=dict(
custom_keys={'backbone': dict(lr_mult=0.1, decay_mult=1.0)}))
optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
# learning policy
lr_config = dict(policy='step', step=110)
runner = dict(type='EpochBasedRunner', max_epochs=150)
project_name = 'detr4seg'
expt_name = 'detr4seg_r101_coco'
work_dir = f'./work_dirs/{expt_name}'
log_config = dict(
interval=50,
hooks=[dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')],
)
load_from = '/mnt/ssd/gzj/test/OpenPSG/detr_r50_fb_origin.pth'
|