Skip to content

Commit

Permalink
add refcoco finetune
Browse files Browse the repository at this point in the history
  • Loading branch information
@hhaAndroid
hhaAndroid committed Dec 14, 2023
1 parent cae8cb3 commit 8a85102
Show file tree
Hide file tree
Showing 11 changed files with 760 additions and 2 deletions.
0 ...nding_dino_swin-t_8xb4_50e_brain_tumor.py → ...o_swin-t_finetune_8xb4_50e_brain_tumor.py
View file
File renamed without changes.
0 ...unding_dino_swin-t_8xb4_50e_cityscapes.py → ...no_swin-t_finetune_8xb4_50e_cityscapes.py
View file
File renamed without changes.
84 changes: 84 additions & 0 deletions configs/grounding_dino_v2/coco/grounding_dino_swin-t_finetune_16xb4_1x_coco.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,84 @@
_base_ = '../grounding_dino_swin-t_pretrain_obj365.py'

data_root = 'data/coco/'

train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RandomFlip', prob=0.5),
dict(
type='RandomChoice',
transforms=[
[
dict(
type='RandomChoiceResize',
scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
keep_ratio=True)
],
[
dict(
type='RandomChoiceResize',
# The radio of all image in train dataset < 7
# follow the original implement
scales=[(400, 4200), (500, 4200), (600, 4200)],
keep_ratio=True),
dict(
type='RandomCrop',
crop_type='absolute_range',
crop_size=(384, 600),
allow_negative_crop=True),
dict(
type='RandomChoiceResize',
scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
keep_ratio=True)
]
]),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'flip', 'flip_direction', 'text',
'custom_entities'))
]

train_dataloader = dict(
dataset=dict(
_delete_=True,
type='CocoDataset',
data_root=data_root,
ann_file='annotations/instances_train2017.json',
data_prefix=dict(img='train2017/'),
return_classes=True,
filter_cfg=dict(filter_empty_gt=False, min_size=32),
pipeline=train_pipeline))

optim_wrapper = dict(
_delete_=True,
type='OptimWrapper',
optimizer=dict(type='AdamW', lr=0.0002, weight_decay=0.0001),
clip_grad=dict(max_norm=0.1, norm_type=2),
paramwise_cfg=dict(custom_keys={
'absolute_pos_embed': dict(decay_mult=0.),
'backbone': dict(lr_mult=0.1),
# 'language_model': dict(lr_mult=0),
}))

# learning policy
max_epochs = 12
param_scheduler = [
dict(
type='MultiStepLR',
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[11],
gamma=0.1)
]
train_cfg = dict(max_epochs=max_epochs, val_interval=1)

default_hooks = dict(checkpoint=dict(max_keep_ckpts=1, save_best='auto'))

load_from = ''
10 changes: 8 additions & 2 deletions ...ding_dino_swin-t_fintune_16xb4_1x_coco.py → ...ing_dino_swin-t_finetune_16xb4_1x_lvis.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,11 @@

data_root = 'data/coco/'

model = dict(test_cfg=dict(
max_per_img=300,
chunked_size=40,
))

train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
Expand Down Expand Up @@ -62,8 +67,9 @@
need_text=False,
label_map_file='annotations/lvis_v1_label_map.json',
ann_file='annotations/lvis_v1_train_od.json',
data_prefix=dict(img='train2017/'),
data_prefix=dict(img=''),
filter_cfg=dict(filter_empty_gt=False, min_size=32),
return_classes=True,
pipeline=train_pipeline)))

val_dataloader = dict(
Expand Down Expand Up @@ -103,7 +109,7 @@
milestones=[11],
gamma=0.1)
]
train_cfg = dict(max_epochs=max_epochs, val_interval=1)
train_cfg = dict(max_epochs=max_epochs, val_interval=3)

default_hooks = dict(checkpoint=dict(max_keep_ckpts=1, save_best='auto'))

Expand Down
0 ...ino_swin-t_8xb4_50e_people_in_painting.py → ...t_finetune_8xb4_50e_people_in_painting.py
View file
File renamed without changes.
167 changes: 167 additions & 0 deletions configs/grounding_dino_v2/refcoco/grounding_dino_swin-t_finetune_grefcoco.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,167 @@
_base_ = '../grounding_dino_swin-t_pretrain_obj365.py'

data_root = 'data/coco/'

train_pipeline = [
dict(type='LoadImageFromFile', backend_args=_base_.backend_args),
dict(type='LoadAnnotations', with_bbox=True),
# change this
dict(type='RandomFlip', prob=0.0),
dict(
type='RandomChoice',
transforms=[
[
dict(
type='RandomChoiceResize',
scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
keep_ratio=True)
],
[
dict(
type='RandomChoiceResize',
# The radio of all image in train dataset < 7
# follow the original implement
scales=[(400, 4200), (500, 4200), (600, 4200)],
keep_ratio=True),
dict(
type='RandomCrop',
crop_type='absolute_range',
crop_size=(384, 600),
allow_negative_crop=True),
dict(
type='RandomChoiceResize',
scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
keep_ratio=True)
]
]),
dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
dict(
type='RandomSamplingNegPos',
tokenizer_name=_base_.lang_model_name,
num_sample_negative=85,
max_tokens=256),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'flip', 'flip_direction', 'text',
'custom_entities', 'tokens_positive', 'dataset_mode'))
]

train_dataloader = dict(
dataset=dict(
_delete_=True,
type='ODVGDataset',
data_root=data_root,
ann_file='mdetr_annotations/finetune_grefcoco_train_vg.json',
data_prefix=dict(img='train2014/'),
filter_cfg=dict(filter_empty_gt=False, min_size=32),
return_classes=True,
pipeline=train_pipeline))

# -------------------------------------------------#
ann_file = 'mdetr_annotations/finetune_grefcoco_val.json'
val_dataset_all_val = dict(
type='MDETRStyleRefCocoDataset',
data_root=data_root,
ann_file=ann_file,
data_prefix=dict(img='train2014/'),
test_mode=True,
return_classes=True,
pipeline=_base_.test_pipeline,
backend_args=None)
val_evaluator_all_val = dict(
type='RefExpMetric',
ann_file=data_root + ann_file,
metric='bbox',
iou_thrs=0.5,
topk=(1, 5, 10))

# -------------------------------------------------#
ann_file = 'mdetr_annotations/finetune_grefcoco_testA.json'
val_dataset_refcoco_testA = dict(
type='MDETRStyleRefCocoDataset',
data_root=data_root,
ann_file=ann_file,
data_prefix=dict(img='train2014/'),
test_mode=True,
return_classes=True,
pipeline=_base_.test_pipeline,
backend_args=None)

val_evaluator_refcoco_testA = dict(
type='RefExpMetric',
ann_file=data_root + ann_file,
metric='bbox',
iou_thrs=0.5,
topk=(1, 5, 10))

# -------------------------------------------------#
ann_file = 'mdetr_annotations/finetune_grefcoco_testB.json'
val_dataset_refcoco_testB = dict(
type='MDETRStyleRefCocoDataset',
data_root=data_root,
ann_file=ann_file,
data_prefix=dict(img='train2014/'),
test_mode=True,
return_classes=True,
pipeline=_base_.test_pipeline,
backend_args=None)

val_evaluator_refcoco_testB = dict(
type='RefExpMetric',
ann_file=data_root + ann_file,
metric='bbox',
iou_thrs=0.5,
topk=(1, 5, 10))

# -------------------------------------------------#
datasets = [val_dataset_all_val, val_dataset_refcoco_testA,
val_dataset_refcoco_testB]
dataset_prefixes = [
'grefcoco_val', 'grefcoco_testA', 'grefcoco_testB'
]
metrics = [val_evaluator_all_val, val_evaluator_refcoco_testA,
val_evaluator_refcoco_testB]

val_dataloader = dict(
dataset=dict(_delete_=True, type='ConcatDataset', datasets=datasets))
test_dataloader = val_dataloader

val_evaluator = dict(
_delete_=True,
type='MultiDatasetsEvaluator',
metrics=metrics,
dataset_prefixes=dataset_prefixes)
test_evaluator = val_evaluator

optim_wrapper = dict(
_delete_=True,
type='OptimWrapper',
optimizer=dict(type='AdamW', lr=0.0002, weight_decay=0.0001),
clip_grad=dict(max_norm=0.1, norm_type=2),
paramwise_cfg=dict(custom_keys={
'absolute_pos_embed': dict(decay_mult=0.),
'backbone': dict(lr_mult=0.1),
# 'language_model': dict(lr_mult=0),
}))

# learning policy
max_epochs = 5
param_scheduler = [
dict(
type='MultiStepLR',
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[3],
gamma=0.1)
]
train_cfg = dict(max_epochs=max_epochs, val_interval=1)

default_hooks = dict(checkpoint=dict(max_keep_ckpts=1, save_best='auto'))

load_from = ''
Loading

0 comments on commit 8a85102

Please sign in to comment.