Commit 77b04ff4 authored by Alexander Nicholas Leye's avatar Alexander Nicholas Leye
Browse files

add bead configs

parent 8a9240f1
dataset_type = 'CocoDataset'
classes = ('chamber','pipe','nebulizer','beading','fog')
data_root = 'data/bead_coco/'
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='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
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=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=1,
train=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'train.json',
img_prefix=data_root + 'images/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'test.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'test.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='bbox')
dataset_type = 'CocoDataset'
classes = ('beading',)
data_root = 'data/bead_cropped_detection/'
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='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
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=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=1,
train=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'train.json',
img_prefix=data_root + 'images/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'test.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'test.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='bbox')
dataset_type = 'CocoDataset'
classes = ('beading',)
data_root = 'data/bead_cropped_detection/'
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='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
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=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=1,
train=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'traintype2lower.json',
img_prefix=data_root + 'images/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'testtype2lower.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'testtype2lower.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='bbox')
dataset_type = 'CocoDataset'
classes = ('beading',)
data_root = 'data/bead_cropped_detection/'
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='LoadImageFromFile'),
dict(type='LoadAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
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=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=1,
train=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'traintype2lower.json',
img_prefix=data_root + 'images/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'testtype2lower.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
classes = classes,
ann_file=data_root + 'testtype2lower.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric=['bbox', 'segm'])
checkpoint_config = dict(interval=1)
checkpoint_config = dict(interval=1, max_keep_ckpts=4)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
dict(type='TensorboardLoggerHook')
])
# yapf:enable
custom_hooks = [dict(type='NumClassCheckHook')]
......
......@@ -8,4 +8,4 @@ lr_config = dict(
warmup_iters=500,
warmup_ratio=0.001,
step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=12)
runner = dict(type='EpochBasedRunner', max_epochs=30)
_base_ = './cascade_mask_rcnn_hrnetv2p_w32_20e_coco.py'
# model settings
model = dict(
pretrained='open-mmlab://msra/hrnetv2_w18',
backbone=dict(
extra=dict(
stage2=dict(num_channels=(18, 36)),
stage3=dict(num_channels=(18, 36, 72)),
stage4=dict(num_channels=(18, 36, 72, 144)))),
neck=dict(type='HRFPN', in_channels=[18, 36, 72, 144], out_channels=256))
_base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py'
model = dict(
pretrained='open-mmlab://msra/hrnetv2_w32',
backbone=dict(
_delete_=True,
type='HRNet',
extra=dict(
stage1=dict(
num_modules=1,
num_branches=1,
block='BOTTLENECK',
num_blocks=(4, ),
num_channels=(64, )),
stage2=dict(
num_modules=1,
num_branches=2,
block='BASIC',
num_blocks=(4, 4),
num_channels=(32, 64)),
stage3=dict(
num_modules=4,
num_branches=3,
block='BASIC',
num_blocks=(4, 4, 4),
num_channels=(32, 64, 128)),
stage4=dict(
num_modules=3,
num_branches=4,
block='BASIC',
num_blocks=(4, 4, 4, 4),
num_channels=(32, 64, 128, 256)))),
neck=dict(
_delete_=True,
type='HRFPN',
in_channels=[32, 64, 128, 256],
out_channels=256))
# learning policy
lr_config = dict(step=[16, 19])
runner = dict(type='EpochBasedRunner', max_epochs=20)
_base_ = './cascade_mask_rcnn_hrnetv2p_w32_20e_coco.py'
# model settings
model = dict(
pretrained='open-mmlab://msra/hrnetv2_w40',
backbone=dict(
type='HRNet',
extra=dict(
stage2=dict(num_channels=(40, 80)),
stage3=dict(num_channels=(40, 80, 160)),
stage4=dict(num_channels=(40, 80, 160, 320)))),
neck=dict(type='HRFPN', in_channels=[40, 80, 160, 320], out_channels=256))
_base_ = './cascade_mask_rcnn_r50_fpn_1x_coco.py'
model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101))
# model settings
model = dict(
type='CascadeRCNN',
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],
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='CascadeRoIHead',
num_stages=3,
stage_loss_weights=[1, 0.5, 0.25],
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.],
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='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
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=[0.05, 0.05, 0.1, 0.1]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
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=[0.033, 0.033, 0.067, 0.067]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=1,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, 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=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=2000,
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),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
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),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
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),
mask_size=28,
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,
mask_thr_binary=0.5)))
_base_ = [
'./cascade_mask_rcnn_r50_fpn.py',
'../_base_/datasets/bead_cropped_type_2_mask.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
_base_ = [
'./cascade_mask_rcnn_swin_fpn.py',
'../_base_/datasets/bead_cropped_type_2.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
model = dict(
backbone=dict(
embed_dim=128,
depths=[2, 2, 18, 2],
num_heads=[4, 8, 16, 32],
window_size=7,
ape=False,
drop_path_rate=0.3,
patch_norm=True,
use_checkpoint=False
),
neck=dict(in_channels=[128, 256, 512, 1024]),
roi_head=dict(
bbox_head=[
dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_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=False,
reg_decoded_bbox=True,
norm_cfg=dict(type='BN', requires_grad=True),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_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=[0.05, 0.05, 0.1, 0.1]),
reg_class_agnostic=False,
reg_decoded_bbox=True,
norm_cfg=dict(type='BN', requires_grad=True),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),
dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,