ship-detection-optical-satellite-hf / redet_re50_refpn_1x_dota_ms_rr_le90.py
jeffaudi's picture
Switching to Airbus training dataset
156088c
raw
history blame contribute delete
No virus
11.6 kB
dataset_type = 'AirbusShipDataset'
data_root = '/data/share/airbus-ship-detection/'
img_norm_cfg = dict(
mean=[52.29048625, 73.2539164, 80.97759001],
std=[53.09640994, 47.58987537, 42.15418378],
to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RResize', img_scale=(768, 768)),
dict(
type='RRandomFlip',
flip_ratio=[0.25, 0.25, 0.25],
direction=['horizontal', 'vertical', 'diagonal'],
version='le90'),
dict(
type='PolyRandomRotate',
rotate_ratio=0.5,
angles_range=180,
auto_bound=False,
version='le90'),
dict(
type='Normalize',
mean=[52.29048625, 73.2539164, 80.97759001],
std=[53.09640994, 47.58987537, 42.15418378],
to_rgb=True),
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=(768, 768),
flip=False,
transforms=[
dict(type='RResize', img_scale=(768, 768)),
dict(
type='Normalize',
mean=[52.29048625, 73.2539164, 80.97759001],
std=[53.09640994, 47.58987537, 42.15418378],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=20,
workers_per_gpu=8,
train=dict(
type='AirbusShipDataset',
ann_file='full.csv',
img_prefix='train_v2/',
metrics_file='metrics_20240328.csv',
oversample_rate=5,
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RResize', img_scale=(768, 768)),
dict(
type='RRandomFlip',
flip_ratio=[0.25, 0.25, 0.25],
direction=['horizontal', 'vertical', 'diagonal'],
version='le90'),
dict(
type='PolyRandomRotate',
rotate_ratio=0.5,
angles_range=180,
auto_bound=False,
version='le90'),
dict(
type='Normalize',
mean=[52.29048625, 73.2539164, 80.97759001],
std=[53.09640994, 47.58987537, 42.15418378],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
],
version='le90',
data_root='/data/share/airbus-ship-detection/'),
val=dict(
type='AirbusShipDataset',
ann_file='valid.csv',
img_prefix='train_v2/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(768, 768),
flip=False,
transforms=[
dict(type='RResize', img_scale=(768, 768)),
dict(
type='Normalize',
mean=[52.29048625, 73.2539164, 80.97759001],
std=[53.09640994, 47.58987537, 42.15418378],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
],
version='le90',
data_root='/data/share/airbus-ship-detection/'),
test=dict(
type='AirbusShipDataset',
ann_file='valid.csv',
img_prefix='train_v2/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(768, 768),
flip=False,
transforms=[
dict(type='RResize', img_scale=(768, 768)),
dict(
type='Normalize',
mean=[52.29048625, 73.2539164, 80.97759001],
std=[53.09640994, 47.58987537, 42.15418378],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
],
version='le90',
data_root='/data/share/airbus-ship-detection/'))
evaluation = dict(interval=2, metric='mAP', save_best='mAP')
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='CosineAnnealing',
warmup='linear',
warmup_iters=2000,
warmup_ratio=0.05,
min_lr_ratio=0.05)
runner = dict(type='EpochBasedRunner', max_epochs=20)
checkpoint_config = dict(interval=10)
log_config = dict(
interval=200,
hooks=[dict(type='TextLoggerHook'),
dict(type='TensorboardLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = 'redet_re50_fpn_1x_dota_ms_rr_le90-fc9217b5.pth'
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
angle_version = 'le90'
model = dict(
type='ReDet',
backbone=dict(
type='ReResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
pretrained='work_dirs/pretrain/re_resnet50_c8_batch256-25b16846.pth'),
neck=dict(
type='ReFPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RotatedRPNHead',
in_channels=256,
feat_channels=256,
version='le90',
anchor_generator=dict(
type='AnchorGenerator',
scales=[2, 4],
ratios=[0.125, 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]),
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='RoITransRoIHead',
version='le90',
num_stages=2,
stage_loss_weights=[1, 1],
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]),
dict(
type='RotatedSingleRoIExtractor',
roi_layer=dict(
type='RiRoIAlignRotated',
out_size=7,
num_samples=2,
num_orientations=16,
clockwise=True),
out_channels=256,
featmap_strides=[4, 8, 16, 32])
],
bbox_head=[
dict(
type='RotatedShared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1,
bbox_coder=dict(
type='DeltaXYWHAHBBoxCoder',
angle_range='le90',
norm_factor=2,
edge_swap=True,
target_means=[0.0, 0.0, 0.0, 0.0, 0.0],
target_stds=[0.1, 0.1, 0.2, 0.2, 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='RotatedShared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=1,
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
angle_range='le90',
norm_factor=None,
edge_swap=True,
proj_xy=True,
target_means=[0.0, 0.0, 0.0, 0.0, 0.0],
target_stds=[0.05, 0.05, 0.1, 0.1, 0.5]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, 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,
gpu_assign_thr=200),
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,
iou_calculator=dict(type='BboxOverlaps2D')),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
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,
iou_calculator=dict(type='RBboxOverlaps2D')),
sampler=dict(
type='RRandomSampler',
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=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
nms_pre=2000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(iou_thr=0.1),
max_per_img=2000)))
img_size = 768
max_keep_ckpts = 1
val_dataloader = dict(samples_per_gpu=20, workers_per_gpu=8)
seed = 1984
gpu_ids = range(0, 1)
device = 'cuda'
work_dir = './logs/redet/2024-03-28-14-45-06'