mmyolo/configs/yolov7/yolov7_l_fast_8x16b-300_coc...

130 lines
3.8 KiB
Python

_base_ = '../_base_/default_runtime.py'
# dataset settings
data_root = 'data/coco/'
dataset_type = 'YOLOv5CocoDataset'
# parameters that often need to be modified
img_scale = (640, 640) # height, width
deepen_factor = 1.0
widen_factor = 1.0
max_epochs = 300
save_epoch_intervals = 10
train_batch_size_per_gpu = 16
train_num_workers = 8
val_batch_size_per_gpu = 1
val_num_workers = 2
# persistent_workers must be False if num_workers is 0.
persistent_workers = True
# only on Val
batch_shapes_cfg = dict(
type='BatchShapePolicy',
batch_size=val_batch_size_per_gpu,
img_size=img_scale[0],
size_divisor=32,
extra_pad_ratio=0.5)
# different from yolov5
anchors = [[(12, 16), (19, 36), (40, 28)], [(36, 75), (76, 55), (72, 146)],
[(142, 110), (192, 243), (459, 401)]]
strides = [8, 16, 32]
# single-scale training is recommended to
# be turned on, which can speed up training.
env_cfg = dict(cudnn_benchmark=True)
model = dict(
type='YOLODetector',
data_preprocessor=dict(
type='YOLOv5DetDataPreprocessor',
mean=[0., 0., 0.],
std=[255., 255., 255.],
bgr_to_rgb=True),
backbone=dict(
type='YOLOv7Backbone',
deepen_factor=deepen_factor,
widen_factor=widen_factor,
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
act_cfg=dict(type='SiLU', inplace=True)),
neck=dict(
type='YOLOv7PAFPN',
deepen_factor=deepen_factor,
widen_factor=widen_factor,
upsample_feats_cat_first=False,
in_channels=[512, 1024, 1024],
out_channels=[128, 256, 512],
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
act_cfg=dict(type='SiLU', inplace=True)),
bbox_head=dict(
type='YOLOv7Head',
head_module=dict(
type='YOLOv5HeadModule',
num_classes=80,
in_channels=[256, 512, 1024],
widen_factor=widen_factor,
featmap_strides=strides,
num_base_priors=3),
prior_generator=dict(
type='mmdet.YOLOAnchorGenerator',
base_sizes=anchors,
strides=strides)),
test_cfg=dict(
multi_label=True,
nms_pre=30000,
score_thr=0.001,
nms=dict(type='nms', iou_threshold=0.65),
max_per_img=300))
test_pipeline = [
dict(
type='LoadImageFromFile',
file_client_args={{_base_.file_client_args}}),
dict(type='YOLOv5KeepRatioResize', scale=img_scale),
dict(
type='LetterResize',
scale=img_scale,
allow_scale_up=False,
pad_val=dict(img=114)),
dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
dict(
type='mmdet.PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'pad_param'))
]
val_dataloader = dict(
batch_size=val_batch_size_per_gpu,
num_workers=val_num_workers,
persistent_workers=persistent_workers,
pin_memory=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
data_root=data_root,
test_mode=True,
data_prefix=dict(img='val2017/'),
ann_file='annotations/instances_val2017.json',
pipeline=test_pipeline,
batch_shapes_cfg=batch_shapes_cfg))
test_dataloader = val_dataloader
val_evaluator = dict(
type='mmdet.CocoMetric',
proposal_nums=(100, 1, 10), # Can be accelerated
ann_file=data_root + 'annotations/instances_val2017.json',
metric='bbox')
test_evaluator = val_evaluator
# train_cfg = dict(
# type='EpochBasedTrainLoop',
# max_epochs=max_epochs,
# val_interval=save_epoch_intervals)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# randomness = dict(seed=1, deterministic=True)