def get_onenet_config(num_classes=80):
h = Config()
input_size = (512, 512)
h.detector = "OneNet"
h.dtype = "float16"
h.data_format = "channels_last"
h.input_shape = (input_size[0], input_size[1], 3)
h.num_classes = num_classes
h.backbone = dict(backbone="ResNet18",
dropblock=None,
normalization=dict(normalization="batch_norm",
momentum=0.997,
epsilon=1e-4,
trainable=False),
activation=dict(activation="relu"),
strides=[2, 2, 2, 2, 2],
dilation_rates=[1, 1, 1, 1, 1],
output_indices=[2, 3, 4, 5],
frozen_stages=[
1,
])
h.neck = dict(neck="CenterNetDeconv",
normalization=dict(normalization="batch_norm",
momentum=0.997,
epsilon=1e-4,
trainable=False),
activation=dict(activation="relu"))
h.head = dict(head="OneNetHead",
activation=dict(activation="relu"),
feat_dims=64,
dropblock=None,
num_classes=num_classes,
strides=4,
prior=0.01,
use_sigmoid=True,
assigner=dict(assigner="MinCostAssigner",
class_weight=2.,
l1_weight=2.,
iou_weight=5.,
iou_type="giou",
alpha=0.25,
gamma=2.),
label_loss=dict(loss="FocalLoss",
alpha=0.25,
gamma=2.,
reduction="sum"),
bbox_loss=dict(loss="RegL1Loss", weight=1., reduction="sum"))
h.weight_decay = 1e-4
h.excluding_weight_names = ["predicted_box", "predicted_class"]
h.train = dict(
dataset=dict(dataset="COCODataset",
batch_size=4,
dataset_dir="/data/bail/COCO",
training=True,
augmentations=[
dict(augmentation="FlipLeftToRight", probability=0.5),
dict(augmentation="RandomDistortColor"),
dict(augmentation="Resize",
img_scale=(0.2, 2),
multiscale_mode="range",
keep_ratio=True),
dict(augmentation="RandCropOrPad",
size=(input_size, input_size),
clip_box_base_center=False),
],
num_samples=118287),
pretrained_weights_path=
"/data/bail/pretrained_weights/resnet50/resnet50.ckpt",
optimizer=dict(optimizer="SGD", momentum=0.9),
mixed_precision=dict(
loss_scale=None
), # The loss scale in mixed precision training. If None, use dynamic.
gradient_clip_norm=10.0,
scheduler=dict(train_epochs=24,
learning_rate_scheduler=dict(
scheduler="PiecewiseConstantDecay",
boundaries=[16, 22],
values=[0.02, 0.002, 0.0002]),
warmup=dict(warmup_learning_rate=0.001, steps=800)),
checkpoint_dir="checkpoints/onenet",
summary_dir="logs/onenet",
log_every_n_steps=100,
save_ckpt_steps=5000)
h.val = dict(dataset=dict(dataset="COCODataset",
batch_size=4,
dataset_dir="/data/bail/COCO",
training=False,
augmentations=[
dict(augmentation="Resize",
img_scale=[(1333, input_size)],
keep_ratio=True),
dict(augmentation="Pad", size_divisor=32)
]),
samples=5000)
h.test = dict(topk=100, score_threshold=0.3)
return h
def get_gfl_config(num_classes=80):
h = Config()
input_size = (1024, 1024)
h.detector = "GFL"
h.dtype = "float16"
h.data_format = "channels_last"
h.input_shape = (input_size[0], input_size[1], 3)
h.num_classes = num_classes
h.backbone = dict(backbone="ResNet101",
dropblock=None,
normalization=dict(normalization="batch_norm", momentum=0.997, epsilon=1e-4, trainable=False),
activation=dict(activation="relu"),
strides=[2, 2, 2, 2, 2],
dilation_rates=[1, 1, 1, 1, 1],
output_indices=[3, 4, 5],
frozen_stages=[1, ])
h.neck=dict(neck="FPN",
feat_dims=256,
min_level=3,
max_level=5,
num_output_levels=5,
add_extra_convs=True,
relu_before_extra_convs=True)
h.anchors=dict(generator="AnchorGeneratorV2",
aspect_ratios=[1.],
octave_base_scale=8,
scales_per_octave=1,
strides=[8, 16, 32, 64, 128],
num_anchors=1)
h.head=dict(head="GFLHead",
normalization=dict(normalization="group_norm", groups=32),
activation=dict(activation="relu"),
feat_dims=256,
dropblock=None,
num_classes=num_classes,
repeats=4,
min_level=3,
max_level=7,
use_sigmoid=True,
prior=0.01,
reg_max=16,
bbox_decoder = dict(decoder="Distance2Box", weights=None),
bbox_encoder = dict(encoder="Box2Distance", weights=None),
assigner = dict(assigner="ATSSAssigner", topk=9),
sampler = dict(sampler="PseudoSampler"),
label_loss = dict(loss="QualityFocalLoss", beta=2.0, weight=1., from_logits=True, reduction="sum"),
bbox_loss = dict(loss="GIoULoss", weight=2., reduction="sum"),
dfl_loss = dict(loss="DistributionFocalLoss", weight=.25, reduction="sum"))
h.weight_decay = 1e-4
h.excluding_weight_names = ["predicted_box", "predicted_class"]
h.train=dict(dataset=dict(dataset="COCODataset",
batch_size=4,
dataset_dir="/data/bail/COCO",
training=True,
augmentations=[
dict(augmentation="FlipLeftToRight", probability=0.5),
dict(augmentation="RandomDistortColor"),
dict(augmentation="Resize", img_scale=[(1333, 800)], keep_ratio=True),
dict(augmentation="Pad", size_divisor=32),
],
num_samples=118287),
pretrained_weights_path="/data/bail/pretrained_weights/resnet50/resnet50.ckpt",
optimizer=dict(optimizer="SGD", momentum=0.9),
mixed_precision=dict(loss_scale=None), # The loss scale in mixed precision training. If None, use dynamic.
gradient_clip_norm=10.0,
scheduler=dict(train_epochs=24,
learning_rate_scheduler=dict(scheduler="PiecewiseConstantDecay",
boundaries=[16, 22],
values=[0.02, 0.002, 0.0002]),
warmup=dict(warmup_learning_rate=0.001, steps=800)),
checkpoint_dir="checkpoints/gfl",
summary_dir="logs/gfl",
log_every_n_steps=100,
save_ckpt_steps=5000)
h.val=dict(dataset=dict(dataset="COCODataset",
batch_size=4,
dataset_dir="/data/bail/COCO",
training=False,
augmentations=[
dict(augmentation="Resize", img_scale=[(1333, 800)], keep_ratio=True),
dict(augmentation="Pad", size_divisor=32),
]),
samples=5000)
h.test=dict(nms="CombinedNonMaxSuppression",
pre_nms_size=5000,
post_nms_size=100,
iou_threshold=0.6,
score_threshold=0.3)
return h
def get_yolov4_config(input_size=None,
num_classes=80,
num_anchors=3,
depth_multiplier=1.,
width_multiplier=1.,
label_assignment="iou",
name="YOLOv4"):
h = Config()
if input_size is None:
input_size = default_input_sizes[name]
h.detector = name
h.dtype = "float16"
h.data_format = "channels_last"
h.num_classes = num_classes
h.depth_multiplier = depth_multiplier_dict[name]
h.width_multiplier = width_multiplier_dict[name]
if name not in model:
raise ValueError(name + " not in ", list(model.keys()))
h.model = model[name]
h.min_level = min_level_dict[name]
h.max_level = max_level_dict[name]
h.strides = strides_dict[name]
h.anchors = anchors_dict[name]
h.num_anchors = len(anchors_dict[name][0]) // 2
h.input_size = input_size if isinstance(input_size, (tuple, list)) else (input_size, input_size)
h.label_assignment = label_assignment
h.anchor_threshold = 0.2
h.gr = 1.
h.bbox_loss = dict(loss="CIoULoss", weight=1., reduction="none")
h.label_loss = dict(loss="BinaryCrossEntropy", weight=1., from_logits=True, reduction="none") # .631 if finetuning else weight = 1.0
h.conf_loss = dict(loss="BinaryCrossEntropy", weight=1., from_logits=True, reduction="none") # 0.911 if finetuning else weight = 1.
h.balance = [1., 1., 1.] # [4.0, 1.0, 0.4] # if num_level == 3 else [4.0, 1.0, 0.4, 0.1]
h.box_weight = 0.05 # 0.0296 if finetune else 0.05
h.label_weight = .5 # 0.243 if finetune else 0.5
h.conf_weight = 1.0 # 0.301 if finetune else 1.0
h.weight_decay = 0.0005
h.excluding_weight_names = ["predicted"]
h.train=dict(dataset=dict(dataset="COCODataset",
batch_size=8,
dataset_dir="/data/bail/COCO",
training=True,
augmentations=[
dict(augmentation="FlipLeftToRight", probability=0.5),
dict(augmentation="RandomDistortColor"),
dict(augmentation="Resize", img_scale=(0.2, 2), keep_ratio=True),
dict(augmentation="Pad", size_divisor=32)
],
# mixup=dict(alpha=8.0, prob=0.5),
mosaic=dict(size=input_size, min_image_scale=0.25, prob=1.),
num_samples=118287),
pretrained_weights_path="/data/bail/pretrained_weights/darknet53-notop/darknet53.ckpt",
optimizer=dict(optimizer="SGD", momentum=0.937),
mixed_precision=dict(loss_scale=None), # The loss scale in mixed precision training. If None, use dynamic.
gradient_clip_norm=.0,
scheduler=dict(train_epochs=480,
# learning_rate_scheduler=dict(scheduler="PiecewiseConstantDecay",
# boundaries=[24, 32],
# values=[0.012, 0.0012, 0.00012]),
learning_rate_scheduler=dict(scheduler="CosineDecay", initial_learning_rate=0.012),
warmup=dict(warmup_learning_rate=0.0012, steps=12000)),
checkpoint_dir="checkpoints/%s" % name,
summary_dir="logs/%s" % name,
log_every_n_steps=100,
save_ckpt_steps=10000)
h.val=dict(dataset=dict(dataset="COCODataset",
batch_size=8,
dataset_dir="/data/bail/COCO",
training=False,
augmentations=[
dict(Resize=dict(size=(input_size, input_size), strides=32, min_scale=1., max_scale=1.0))
# dict(ResizeV2=dict(short_side=800, long_side=1333, strides=64, min_scale=1.0, max_scale=1.0))
]),
samples=5000)
# h.test=dict(nms="NonMaxSuppressionWithQuality",
# pre_nms_size=5000,
# post_nms_size=100,
# iou_threshold=0.6,
# score_threshold=0.5,
# sigma=0.5,
# nms_type="nms")
h.test=dict(nms="CombinedNonMaxSuppression",
pre_nms_size=2000,
post_nms_size=100,
iou_threshold=0.6,
score_threshold=0.35)
return h
def get_yolof_config(num_classes=80):
h = Config()
data_format = "channels_last"
input_size = (1024, 1024)
h.detector = "YOLOF"
h.dtype = "float16"
h.data_format = data_format
h.input_shape = (input_size[0], input_size[1], 3)
h.num_classes = num_classes
h.backbone = dict(backbone="ResNeXt101_64X4D",
dropblock=None,
normalization=dict(normalization="batch_norm", momentum=0.997, epsilon=1e-4, trainable=False),
activation=dict(activation="relu"),
strides=[2, 2, 2, 2, 2],
dilation_rates=[1, 1, 1, 1, 1],
output_indices=[5],
frozen_stages=[1, ])
h.neck=dict(neck="DilatedEncoder",
filters=512,
midfilters=128,
dilation_rates=[2, 4, 6, 8], # dilation not in stage5
# dilation_rates=[4, 8, 12, 16],
normalization=dict(normalization="batch_norm", momentum=0.9, epsilon=1e-3, axis=-1, trainable=True),
activation=dict(activation="relu"),
kernel_initializer="he_normal",
data_format=data_format)
h.anchors=dict(generator="AnchorGenerator",
aspect_ratios=[1.],
scales=[32, 64, 128, 256, 512],
strides=32,
# scales=[16, 32, 64, 128, 256, 512],
# strides=16,
num_anchors=5)
h.head=dict(head="YOLOFHead",
normalization=dict(normalization="batch_norm", momentum=0.9, epsilon=1e-3, axis=-1, trainable=True),
activation=dict(activation="relu"),
feat_dims=512,
cls_num_convs=2,
reg_num_convs=4,
kernel_initializer="he_normal",
use_sigmoid=True,
prior=0.01,
bbox_decoder=dict(decoder="Delta2Box", weights=[1., 1., 1., 1.]),
bbox_encoder=dict(encoder="Box2Delta", weights=[1., 1., 1., 1.]),
assigner=dict(assigner="UniformAssigner", match_times=8, pos_ignore_thresh=0.7, neg_ignore_thresh=0.15),
sampler=dict(sampler="PseudoSampler"),
label_loss=dict(loss="FocalLoss", alpha=0.25, gamma=2.0, weight=1., from_logits=True, reduction="sum"),
bbox_loss=dict(loss="GIoULoss", weight=2., reduction="sum"))
h.weight_decay = 1e-4
h.excluding_weight_names = ["predicted_box", "predicted_class"]
h.train=dict(dataset=dict(dataset="COCODataset",
batch_size=4,
dataset_dir="/data/bail/COCO",
training=True,
augmentations=[
dict(augmentation="FlipLeftToRight", probability=0.5),
dict(augmentation="RandomDistortColor"),
dict(augmentation="Resize", img_scale=[(1333, 800)], keep_ratio=True),
dict(augmentation="Pad", size_divisor=32)
],
num_samples=118287),
pretrained_weights_path="/data/bail/pretrained_weights/resnet50/resnet50.ckpt",
optimizer=dict(optimizer="SGD", momentum=0.9),
mixed_precision=dict(loss_scale=None), # The loss scale in mixed precision training. If None, use dynamic.
gradient_clip_norm=10.0,
scheduler=dict(train_epochs=24,
learning_rate_scheduler=dict(scheduler="PiecewiseConstantDecay",
boundaries=[16, 22],
values=[0.02, 0.002, 0.0002]),
warmup=dict(warmup_learning_rate=0.001, steps=800)),
checkpoint_dir="checkpoints/yolof",
summary_dir="logs/yolof",
log_every_n_steps=100,
save_ckpt_steps=5000)
h.val=dict(dataset=dict(dataset="COCODataset",
batch_size=4,
dataset_dir="/data/bail/COCO",
training=False,
augmentations=[
dict(augmentation="Resize", img_scale=[(1333, 800)], keep_ratio=True),
dict(augmentation="Pad", size_divisor=32),
]),
samples=5000)
h.test=dict(nms="CombinedNonMaxSuppression",
pre_nms_size=2000,
post_nms_size=100,
iou_threshold=0.5,
score_threshold=0.35)
return h
