mirror of https://github.com/open-mmlab/mmyolo.git
[Improve] Beautify the YOLOv7 configuration (#506)
* Beautify the YOLOv7 configuration * yolov7 config * Update configs/yolov7/yolov7_l_syncbn_fast_8x16b-300e_coco.py Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com> * Update configs/yolov7/yolov7_tiny_syncbn_fast_8x16b-300e_coco.py Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com> * Update configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com> * Update configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com> * Update configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com> * Update configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com> * Beautify the YOLOv7 configuration --------- Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>pull/547/head
tianlei
GitHub
parent
d8b1353691
commit
4e8bf17c90
|
|
@ -1,42 +1,103 @@
|
|||
_base_ = '../_base_/default_runtime.py'
|
||||
|
||||
# dataset settings
|
||||
data_root = 'data/coco/'
|
||||
dataset_type = 'YOLOv5CocoDataset'
|
||||
# ========================Frequently modified parameters======================
|
||||
# -----data related-----
|
||||
data_root = 'data/coco/' # Root path of data
|
||||
# Path of train annotation file
|
||||
train_ann_file = 'annotations/instances_train2017.json'
|
||||
train_data_prefix = 'train2017/' # Prefix of train image path
|
||||
# Path of val annotation file
|
||||
val_ann_file = 'annotations/instances_val2017.json'
|
||||
val_data_prefix = 'val2017/' # Prefix of val image path
|
||||
|
||||
# parameters that often need to be modified
|
||||
img_scale = (640, 640) # width, height
|
||||
max_epochs = 300
|
||||
save_epoch_intervals = 10
|
||||
num_classes = 80 # Number of classes for classification
|
||||
# Batch size of a single GPU during training
|
||||
train_batch_size_per_gpu = 16
|
||||
# Worker to pre-fetch data for each single GPU during training
|
||||
train_num_workers = 8
|
||||
# persistent_workers must be False if num_workers is 0.
|
||||
# persistent_workers must be False if num_workers is 0
|
||||
persistent_workers = True
|
||||
val_batch_size_per_gpu = 1
|
||||
val_num_workers = 2
|
||||
|
||||
# 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
|
||||
# -----model related-----
|
||||
# Basic size of multi-scale prior box
|
||||
anchors = [
|
||||
[(12, 16), (19, 36), (40, 28)], # P3/8
|
||||
[(36, 75), (76, 55), (72, 146)], # P4/16
|
||||
[(142, 110), (192, 243), (459, 401)] # P5/32
|
||||
]
|
||||
strides = [8, 16, 32]
|
||||
num_det_layers = 3
|
||||
num_classes = 80
|
||||
# -----train val related-----
|
||||
# Base learning rate for optim_wrapper. Corresponding to 8xb16=64 bs
|
||||
base_lr = 0.01
|
||||
max_epochs = 300 # Maximum training epochs
|
||||
|
||||
# single-scale training is recommended to
|
||||
num_epoch_stage2 = 30 # The last 30 epochs switch evaluation interval
|
||||
val_interval_stage2 = 1 # Evaluation interval
|
||||
|
||||
model_test_cfg = dict(
|
||||
# The config of multi-label for multi-class prediction.
|
||||
multi_label=True,
|
||||
# The number of boxes before NMS.
|
||||
nms_pre=30000,
|
||||
score_thr=0.001, # Threshold to filter out boxes.
|
||||
nms=dict(type='nms', iou_threshold=0.65), # NMS type and threshold
|
||||
max_per_img=300) # Max number of detections of each image
|
||||
|
||||
# ========================Possible modified parameters========================
|
||||
# -----data related-----
|
||||
img_scale = (640, 640) # width, height
|
||||
# Dataset type, this will be used to define the dataset
|
||||
dataset_type = 'YOLOv5CocoDataset'
|
||||
# Batch size of a single GPU during validation
|
||||
val_batch_size_per_gpu = 1
|
||||
# Worker to pre-fetch data for each single GPU during validation
|
||||
val_num_workers = 2
|
||||
|
||||
# Config of batch shapes. Only on val.
|
||||
# It means not used if batch_shapes_cfg is None.
|
||||
batch_shapes_cfg = dict(
|
||||
type='BatchShapePolicy',
|
||||
batch_size=val_batch_size_per_gpu,
|
||||
img_size=img_scale[0],
|
||||
# The image scale of padding should be divided by pad_size_divisor
|
||||
size_divisor=32,
|
||||
# Additional paddings for pixel scale
|
||||
extra_pad_ratio=0.5)
|
||||
|
||||
# -----model related-----
|
||||
strides = [8, 16, 32] # Strides of multi-scale prior box
|
||||
num_det_layers = 3 # The number of model output scales
|
||||
norm_cfg = dict(type='BN', momentum=0.03, eps=0.001)
|
||||
|
||||
# Data augmentation
|
||||
max_translate_ratio = 0.2 # YOLOv5RandomAffine
|
||||
scaling_ratio_range = (0.1, 2.0) # YOLOv5RandomAffine
|
||||
mixup_prob = 0.15 # YOLOv5MixUp
|
||||
randchoice_mosaic_prob = [0.8, 0.2]
|
||||
mixup_alpha = 8.0 # YOLOv5MixUp
|
||||
mixup_beta = 8.0 # YOLOv5MixUp
|
||||
|
||||
# -----train val related-----
|
||||
loss_cls_weight = 0.3
|
||||
loss_bbox_weight = 0.05
|
||||
loss_obj_weight = 0.7
|
||||
# BatchYOLOv7Assigner params
|
||||
simota_candidate_topk = 10
|
||||
simota_iou_weight = 3.0
|
||||
simota_cls_weight = 1.0
|
||||
prior_match_thr = 4. # Priori box matching threshold
|
||||
obj_level_weights = [4., 1.,
|
||||
0.4] # The obj loss weights of the three output layers
|
||||
|
||||
lr_factor = 0.1 # Learning rate scaling factor
|
||||
weight_decay = 0.0005
|
||||
save_epoch_intervals = 1 # Save model checkpoint and validation intervals
|
||||
max_keep_ckpts = 3 # The maximum checkpoints to keep.
|
||||
|
||||
# Single-scale training is recommended to
|
||||
# be turned on, which can speed up training.
|
||||
env_cfg = dict(cudnn_benchmark=True)
|
||||
|
||||
# ===============================Unmodified in most cases====================
|
||||
model = dict(
|
||||
type='YOLODetector',
|
||||
data_preprocessor=dict(
|
||||
|
|
@ -47,7 +108,7 @@ model = dict(
|
|||
backbone=dict(
|
||||
type='YOLOv7Backbone',
|
||||
arch='L',
|
||||
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
|
||||
norm_cfg=norm_cfg,
|
||||
act_cfg=dict(type='SiLU', inplace=True)),
|
||||
neck=dict(
|
||||
type='YOLOv7PAFPN',
|
||||
|
|
@ -61,7 +122,7 @@ model = dict(
|
|||
in_channels=[512, 1024, 1024],
|
||||
# The real output channel will be multiplied by 2
|
||||
out_channels=[128, 256, 512],
|
||||
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
|
||||
norm_cfg=norm_cfg,
|
||||
act_cfg=dict(type='SiLU', inplace=True)),
|
||||
bbox_head=dict(
|
||||
type='YOLOv7Head',
|
||||
|
|
@ -80,31 +141,28 @@ model = dict(
|
|||
type='mmdet.CrossEntropyLoss',
|
||||
use_sigmoid=True,
|
||||
reduction='mean',
|
||||
loss_weight=0.3 * (num_classes / 80 * 3 / num_det_layers)),
|
||||
loss_weight=loss_cls_weight *
|
||||
(num_classes / 80 * 3 / num_det_layers)),
|
||||
loss_bbox=dict(
|
||||
type='IoULoss',
|
||||
iou_mode='ciou',
|
||||
bbox_format='xywh',
|
||||
reduction='mean',
|
||||
loss_weight=0.05 * (3 / num_det_layers),
|
||||
loss_weight=loss_bbox_weight * (3 / num_det_layers),
|
||||
return_iou=True),
|
||||
loss_obj=dict(
|
||||
type='mmdet.CrossEntropyLoss',
|
||||
use_sigmoid=True,
|
||||
reduction='mean',
|
||||
loss_weight=0.7 * ((img_scale[0] / 640)**2 * 3 / num_det_layers)),
|
||||
obj_level_weights=[4., 1., 0.4],
|
||||
loss_weight=loss_obj_weight *
|
||||
((img_scale[0] / 640)**2 * 3 / num_det_layers)),
|
||||
prior_match_thr=prior_match_thr,
|
||||
obj_level_weights=obj_level_weights,
|
||||
# BatchYOLOv7Assigner params
|
||||
prior_match_thr=4.,
|
||||
simota_candidate_topk=10,
|
||||
simota_iou_weight=3.0,
|
||||
simota_cls_weight=1.0),
|
||||
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))
|
||||
simota_candidate_topk=simota_candidate_topk,
|
||||
simota_iou_weight=simota_iou_weight,
|
||||
simota_cls_weight=simota_cls_weight),
|
||||
test_cfg=model_test_cfg)
|
||||
|
||||
pre_transform = [
|
||||
dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
|
||||
|
|
@ -121,8 +179,8 @@ mosiac4_pipeline = [
|
|||
type='YOLOv5RandomAffine',
|
||||
max_rotate_degree=0.0,
|
||||
max_shear_degree=0.0,
|
||||
max_translate_ratio=0.2, # note
|
||||
scaling_ratio_range=(0.1, 2.0), # note
|
||||
max_translate_ratio=max_translate_ratio, # note
|
||||
scaling_ratio_range=scaling_ratio_range, # note
|
||||
# img_scale is (width, height)
|
||||
border=(-img_scale[0] // 2, -img_scale[1] // 2),
|
||||
border_val=(114, 114, 114)),
|
||||
|
|
@ -138,8 +196,8 @@ mosiac9_pipeline = [
|
|||
type='YOLOv5RandomAffine',
|
||||
max_rotate_degree=0.0,
|
||||
max_shear_degree=0.0,
|
||||
max_translate_ratio=0.2, # note
|
||||
scaling_ratio_range=(0.1, 2.0), # note
|
||||
max_translate_ratio=max_translate_ratio, # note
|
||||
scaling_ratio_range=scaling_ratio_range, # note
|
||||
# img_scale is (width, height)
|
||||
border=(-img_scale[0] // 2, -img_scale[1] // 2),
|
||||
border_val=(114, 114, 114)),
|
||||
|
|
@ -148,16 +206,16 @@ mosiac9_pipeline = [
|
|||
randchoice_mosaic_pipeline = dict(
|
||||
type='RandomChoice',
|
||||
transforms=[mosiac4_pipeline, mosiac9_pipeline],
|
||||
prob=[0.8, 0.2])
|
||||
prob=randchoice_mosaic_prob)
|
||||
|
||||
train_pipeline = [
|
||||
*pre_transform,
|
||||
randchoice_mosaic_pipeline,
|
||||
dict(
|
||||
type='YOLOv5MixUp',
|
||||
alpha=8.0, # note
|
||||
beta=8.0, # note
|
||||
prob=0.15,
|
||||
alpha=mixup_alpha, # note
|
||||
beta=mixup_beta, # note
|
||||
prob=mixup_prob,
|
||||
pre_transform=[*pre_transform, randchoice_mosaic_pipeline]),
|
||||
dict(type='YOLOv5HSVRandomAug'),
|
||||
dict(type='mmdet.RandomFlip', prob=0.5),
|
||||
|
|
@ -177,8 +235,8 @@ train_dataloader = dict(
|
|||
dataset=dict(
|
||||
type=dataset_type,
|
||||
data_root=data_root,
|
||||
ann_file='annotations/instances_train2017.json',
|
||||
data_prefix=dict(img='train2017/'),
|
||||
ann_file=train_ann_file,
|
||||
data_prefix=dict(img=train_data_prefix),
|
||||
filter_cfg=dict(filter_empty_gt=False, min_size=32),
|
||||
pipeline=train_pipeline))
|
||||
|
||||
|
|
@ -208,8 +266,8 @@ val_dataloader = dict(
|
|||
type=dataset_type,
|
||||
data_root=data_root,
|
||||
test_mode=True,
|
||||
data_prefix=dict(img='val2017/'),
|
||||
ann_file='annotations/instances_val2017.json',
|
||||
data_prefix=dict(img=val_data_prefix),
|
||||
ann_file=val_ann_file,
|
||||
pipeline=test_pipeline,
|
||||
batch_shapes_cfg=batch_shapes_cfg))
|
||||
|
||||
|
|
@ -220,9 +278,9 @@ optim_wrapper = dict(
|
|||
type='OptimWrapper',
|
||||
optimizer=dict(
|
||||
type='SGD',
|
||||
lr=0.01,
|
||||
lr=base_lr,
|
||||
momentum=0.937,
|
||||
weight_decay=0.0005,
|
||||
weight_decay=weight_decay,
|
||||
nesterov=True,
|
||||
batch_size_per_gpu=train_batch_size_per_gpu),
|
||||
constructor='YOLOv7OptimWrapperConstructor')
|
||||
|
|
@ -231,27 +289,14 @@ default_hooks = dict(
|
|||
param_scheduler=dict(
|
||||
type='YOLOv5ParamSchedulerHook',
|
||||
scheduler_type='cosine',
|
||||
lr_factor=0.1, # note
|
||||
lr_factor=lr_factor, # note
|
||||
max_epochs=max_epochs),
|
||||
checkpoint=dict(
|
||||
type='CheckpointHook',
|
||||
save_param_scheduler=False,
|
||||
interval=1,
|
||||
interval=save_epoch_intervals,
|
||||
save_best='auto',
|
||||
max_keep_ckpts=3))
|
||||
|
||||
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,
|
||||
dynamic_intervals=[(270, 1)])
|
||||
max_keep_ckpts=max_keep_ckpts))
|
||||
|
||||
custom_hooks = [
|
||||
dict(
|
||||
|
|
@ -263,7 +308,17 @@ custom_hooks = [
|
|||
priority=49)
|
||||
]
|
||||
|
||||
val_evaluator = dict(
|
||||
type='mmdet.CocoMetric',
|
||||
proposal_nums=(100, 1, 10), # Can be accelerated
|
||||
ann_file=data_root + val_ann_file,
|
||||
metric='bbox')
|
||||
test_evaluator = val_evaluator
|
||||
|
||||
train_cfg = dict(
|
||||
type='EpochBasedTrainLoop',
|
||||
max_epochs=max_epochs,
|
||||
val_interval=save_epoch_intervals,
|
||||
dynamic_intervals=[(max_epochs - num_epoch_stage2, val_interval_stage2)])
|
||||
val_cfg = dict(type='ValLoop')
|
||||
test_cfg = dict(type='TestLoop')
|
||||
|
||||
# randomness = dict(seed=1, deterministic=True)
|
||||
|
|
|
|||
|
|
@ -1,10 +1,26 @@
|
|||
_base_ = './yolov7_l_syncbn_fast_8x16b-300e_coco.py'
|
||||
|
||||
# ========================modified parameters========================
|
||||
|
||||
# -----model related-----
|
||||
# Data augmentation
|
||||
max_translate_ratio = 0.1 # YOLOv5RandomAffine
|
||||
scaling_ratio_range = (0.5, 1.6) # YOLOv5RandomAffine
|
||||
mixup_prob = 0.05 # YOLOv5MixUp
|
||||
randchoice_mosaic_prob = [0.8, 0.2]
|
||||
mixup_alpha = 8.0 # YOLOv5MixUp
|
||||
mixup_beta = 8.0 # YOLOv5MixUp
|
||||
|
||||
# -----train val related-----
|
||||
loss_cls_weight = 0.5
|
||||
loss_obj_weight = 1.0
|
||||
|
||||
lr_factor = 0.01 # Learning rate scaling factor
|
||||
# ===============================Unmodified in most cases====================
|
||||
num_classes = _base_.num_classes
|
||||
num_det_layers = _base_.num_det_layers
|
||||
img_scale = _base_.img_scale
|
||||
pre_transform = _base_.pre_transform
|
||||
|
||||
model = dict(
|
||||
backbone=dict(
|
||||
arch='Tiny', act_cfg=dict(type='LeakyReLU', negative_slope=0.1)),
|
||||
|
|
@ -18,9 +34,9 @@ model = dict(
|
|||
use_repconv_outs=False),
|
||||
bbox_head=dict(
|
||||
head_module=dict(in_channels=[128, 256, 512]),
|
||||
loss_cls=dict(loss_weight=0.5 *
|
||||
loss_cls=dict(loss_weight=loss_cls_weight *
|
||||
(num_classes / 80 * 3 / num_det_layers)),
|
||||
loss_obj=dict(loss_weight=1.0 *
|
||||
loss_obj=dict(loss_weight=loss_obj_weight *
|
||||
((img_scale[0] / 640)**2 * 3 / num_det_layers))))
|
||||
|
||||
mosiac4_pipeline = [
|
||||
|
|
@ -33,8 +49,8 @@ mosiac4_pipeline = [
|
|||
type='YOLOv5RandomAffine',
|
||||
max_rotate_degree=0.0,
|
||||
max_shear_degree=0.0,
|
||||
max_translate_ratio=0.1, # change
|
||||
scaling_ratio_range=(0.5, 1.6), # change
|
||||
max_translate_ratio=max_translate_ratio, # change
|
||||
scaling_ratio_range=scaling_ratio_range, # change
|
||||
# img_scale is (width, height)
|
||||
border=(-img_scale[0] // 2, -img_scale[1] // 2),
|
||||
border_val=(114, 114, 114)),
|
||||
|
|
@ -50,8 +66,8 @@ mosiac9_pipeline = [
|
|||
type='YOLOv5RandomAffine',
|
||||
max_rotate_degree=0.0,
|
||||
max_shear_degree=0.0,
|
||||
max_translate_ratio=0.1, # change
|
||||
scaling_ratio_range=(0.5, 1.6), # change
|
||||
max_translate_ratio=max_translate_ratio, # change
|
||||
scaling_ratio_range=scaling_ratio_range, # change
|
||||
border=(-img_scale[0] // 2, -img_scale[1] // 2),
|
||||
border_val=(114, 114, 114)),
|
||||
]
|
||||
|
|
@ -59,16 +75,16 @@ mosiac9_pipeline = [
|
|||
randchoice_mosaic_pipeline = dict(
|
||||
type='RandomChoice',
|
||||
transforms=[mosiac4_pipeline, mosiac9_pipeline],
|
||||
prob=[0.8, 0.2])
|
||||
prob=randchoice_mosaic_prob)
|
||||
|
||||
train_pipeline = [
|
||||
*pre_transform,
|
||||
randchoice_mosaic_pipeline,
|
||||
dict(
|
||||
type='YOLOv5MixUp',
|
||||
alpha=8.0,
|
||||
beta=8.0,
|
||||
prob=0.05, # change
|
||||
alpha=mixup_alpha,
|
||||
beta=mixup_beta,
|
||||
prob=mixup_prob, # change
|
||||
pre_transform=[*pre_transform, randchoice_mosaic_pipeline]),
|
||||
dict(type='YOLOv5HSVRandomAug'),
|
||||
dict(type='mmdet.RandomFlip', prob=0.5),
|
||||
|
|
@ -79,4 +95,4 @@ train_pipeline = [
|
|||
]
|
||||
|
||||
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
|
||||
default_hooks = dict(param_scheduler=dict(lr_factor=0.01))
|
||||
default_hooks = dict(param_scheduler=dict(lr_factor=lr_factor))
|
||||
|
|
|
|||
|
|
@ -1,19 +1,42 @@
|
|||
_base_ = './yolov7_l_syncbn_fast_8x16b-300e_coco.py'
|
||||
|
||||
# ========================modified parameters========================
|
||||
# -----data related-----
|
||||
img_scale = (1280, 1280) # height, width
|
||||
num_classes = 80
|
||||
# only on Val
|
||||
batch_shapes_cfg = dict(img_size=img_scale[0], size_divisor=64)
|
||||
num_classes = 80 # Number of classes for classification
|
||||
# Config of batch shapes. Only on val
|
||||
# It means not used if batch_shapes_cfg is None.
|
||||
batch_shapes_cfg = dict(
|
||||
img_size=img_scale[
|
||||
0], # The image scale of padding should be divided by pad_size_divisor
|
||||
size_divisor=64) # Additional paddings for pixel scale
|
||||
|
||||
# -----model related-----
|
||||
# Basic size of multi-scale prior box
|
||||
anchors = [
|
||||
[(19, 27), (44, 40), (38, 94)], # P3/8
|
||||
[(96, 68), (86, 152), (180, 137)], # P4/16
|
||||
[(140, 301), (303, 264), (238, 542)], # P5/32
|
||||
[(436, 615), (739, 380), (925, 792)] # P6/64
|
||||
]
|
||||
strides = [8, 16, 32, 64]
|
||||
num_det_layers = 4
|
||||
strides = [8, 16, 32, 64] # Strides of multi-scale prior box
|
||||
num_det_layers = 4 # # The number of model output scales
|
||||
norm_cfg = dict(type='BN', momentum=0.03, eps=0.001)
|
||||
|
||||
# Data augmentation
|
||||
max_translate_ratio = 0.2 # YOLOv5RandomAffine
|
||||
scaling_ratio_range = (0.1, 2.0) # YOLOv5RandomAffine
|
||||
mixup_prob = 0.15 # YOLOv5MixUp
|
||||
randchoice_mosaic_prob = [0.8, 0.2]
|
||||
mixup_alpha = 8.0 # YOLOv5MixUp
|
||||
mixup_beta = 8.0 # YOLOv5MixUp
|
||||
|
||||
# -----train val related-----
|
||||
loss_cls_weight = 0.3
|
||||
loss_bbox_weight = 0.05
|
||||
loss_obj_weight = 0.7
|
||||
|
||||
# ===============================Unmodified in most cases====================
|
||||
model = dict(
|
||||
backbone=dict(arch='W', out_indices=(2, 3, 4, 5)),
|
||||
neck=dict(
|
||||
|
|
@ -26,15 +49,15 @@ model = dict(
|
|||
type='YOLOv7p6HeadModule',
|
||||
in_channels=[128, 256, 384, 512],
|
||||
featmap_strides=strides,
|
||||
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
|
||||
norm_cfg=norm_cfg,
|
||||
act_cfg=dict(type='SiLU', inplace=True)),
|
||||
prior_generator=dict(base_sizes=anchors, strides=strides),
|
||||
simota_candidate_topk=20, # note
|
||||
# scaled based on number of detection layers
|
||||
loss_cls=dict(loss_weight=0.3 *
|
||||
loss_cls=dict(loss_weight=loss_cls_weight *
|
||||
(num_classes / 80 * 3 / num_det_layers)),
|
||||
loss_bbox=dict(loss_weight=0.05 * (3 / num_det_layers)),
|
||||
loss_obj=dict(loss_weight=0.7 *
|
||||
loss_bbox=dict(loss_weight=loss_bbox_weight * (3 / num_det_layers)),
|
||||
loss_obj=dict(loss_weight=loss_obj_weight *
|
||||
((img_scale[0] / 640)**2 * 3 / num_det_layers)),
|
||||
obj_level_weights=[4.0, 1.0, 0.25, 0.06]))
|
||||
|
||||
|
|
@ -50,8 +73,8 @@ mosiac4_pipeline = [
|
|||
type='YOLOv5RandomAffine',
|
||||
max_rotate_degree=0.0,
|
||||
max_shear_degree=0.0,
|
||||
max_translate_ratio=0.2, # note
|
||||
scaling_ratio_range=(0.1, 2.0), # note
|
||||
max_translate_ratio=max_translate_ratio, # note
|
||||
scaling_ratio_range=scaling_ratio_range, # note
|
||||
# img_scale is (width, height)
|
||||
border=(-img_scale[0] // 2, -img_scale[1] // 2),
|
||||
border_val=(114, 114, 114)),
|
||||
|
|
@ -67,8 +90,8 @@ mosiac9_pipeline = [
|
|||
type='YOLOv5RandomAffine',
|
||||
max_rotate_degree=0.0,
|
||||
max_shear_degree=0.0,
|
||||
max_translate_ratio=0.2, # note
|
||||
scaling_ratio_range=(0.1, 2.0), # note
|
||||
max_translate_ratio=max_translate_ratio, # note
|
||||
scaling_ratio_range=scaling_ratio_range, # note
|
||||
# img_scale is (width, height)
|
||||
border=(-img_scale[0] // 2, -img_scale[1] // 2),
|
||||
border_val=(114, 114, 114)),
|
||||
|
|
@ -77,16 +100,16 @@ mosiac9_pipeline = [
|
|||
randchoice_mosaic_pipeline = dict(
|
||||
type='RandomChoice',
|
||||
transforms=[mosiac4_pipeline, mosiac9_pipeline],
|
||||
prob=[0.8, 0.2])
|
||||
prob=randchoice_mosaic_prob)
|
||||
|
||||
train_pipeline = [
|
||||
*pre_transform,
|
||||
randchoice_mosaic_pipeline,
|
||||
dict(
|
||||
type='YOLOv5MixUp',
|
||||
alpha=8.0, # note
|
||||
beta=8.0, # note
|
||||
prob=0.15,
|
||||
alpha=mixup_alpha, # note
|
||||
beta=mixup_beta, # note
|
||||
prob=mixup_prob,
|
||||
pre_transform=[*pre_transform, randchoice_mosaic_pipeline]),
|
||||
dict(type='YOLOv5HSVRandomAug'),
|
||||
dict(type='mmdet.RandomFlip', prob=0.5),
|
||||
|
|
|
|||
Loading…
Reference in New Issue