def __init__(self, cfg=None, phase='train'):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(Retina, self).__init__()
self.phase = phase
backbone = None
if cfg['name'] == 'mobilenet0.25':
backbone = MobileNetV1()
self.body = _utils.IntermediateLayerGetter(backbone, cfg['return_layers'])
in_channels_stage2 = cfg['in_channel']
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list, out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3, inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=3, inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(fpn_num=3, inchannels=cfg['out_channel'])
def __init__(self, cfg=None, phase='train'):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace, self).__init__()
self.phase = phase
backbone = models.mobilenet_v2(pretrained=cfg['pretrain'], width_mult=cfg['width_mult']).features
self.body = _utils.IntermediateLayerGetter(backbone, cfg['return_layers'])
in_channels_list = [
cfg['in_channel'][0],
cfg['in_channel'][1],
cfg['in_channel'][2],
]
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list, out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3, inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=3, inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(fpn_num=3, inchannels=cfg['out_channel'])
def __init__(self, cfg=None, phase='train'):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace, self).__init__()
self.cfg = cfg
self.phase = phase
backbone = None
if cfg['name'] == 'mobilenet0.25':
backbone = MobileNetV1()
if cfg['pretrain']:
checkpoint = torch.load(
"./weights/mobilenetV1X0.25_pretrain.tar",
map_location=torch.device('cpu'))
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in checkpoint['state_dict'].items():
name = k[7:] # remove module.
new_state_dict[name] = v
# load params
backbone.load_state_dict(new_state_dict)
elif cfg['name'] == 'Resnet50':
import torchvision.models as models
backbone = models.resnet50(pretrained=cfg['pretrain'])
elif cfg['name'] == 'effnet':
self.body = load_effnetm()
elif cfg['name'] == 'Res2Net':
from .res2net import res2net101_26w_4s
model = res2net101_26w_4s(pretrained=True)
self.body = _utils.IntermediateLayerGetter(model,
cfg['return_layers'])
if cfg['name'] == 'mobilenet0.25' or cfg['name'] == 'Resnet50':
self.body = _utils.IntermediateLayerGetter(backbone,
cfg['return_layers'])
in_channels_stage2 = cfg['in_channel']
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
if cfg['name'] == 'effnet':
in_channels_list = [64, 176, 512]
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list, out_channels, cfg)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(
fpn_num=3, inchannels=cfg['out_channel'])
def __init__(self, cfg=None, phase='train'):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace, self).__init__()
self.phase = phase
backbone = None
if cfg['name'] == 'mobilenet0.25':
backbone = MobileNetV1()
if cfg['pretrain']:
checkpoint = torch.load(
"./weights/mobilenetV1X0.25_pretrain.tar",
map_location=torch.device('cpu'))
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in checkpoint['state_dict'].items():
name = k[7:] # remove module.
new_state_dict[name] = v
# load params
backbone.load_state_dict(new_state_dict)
elif cfg['name'] == 'Resnet50':
import torchvision.models as models
backbone = models.resnet50(pretrained=cfg['pretrain'])
# 获取中间层输出
self.body = _utils.IntermediateLayerGetter(backbone,
cfg['return_layers'])
in_channels_stage2 = cfg['in_channel']
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list, out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
# 参考口罩分支，ssh单独新建
self.ssh1_pose = SSH(out_channels, out_channels)
self.ssh2_pose = SSH(out_channels, out_channels)
self.ssh3_pose = SSH(out_channels, out_channels)
# 对应ssh 的 框-关键点-2分类
self.ClassHead = self._make_class_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(
fpn_num=3, inchannels=cfg['out_channel'])
# 对应ssh_pose 的 yaw-pitch-roll 的 3个66分类
self.Pose_yaw_Head = self._make_pose_yaw_pitch_roll_head(
fpn_num=3, inchannels=cfg['out_channel'])
self.Pose_pitch_Head = self._make_pose_yaw_pitch_roll_head(
fpn_num=3, inchannels=cfg['out_channel'])
self.Pose_roll_Head = self._make_pose_yaw_pitch_roll_head(
fpn_num=3, inchannels=cfg['out_channel'])
def __init__(
self,
cfg=None,
phase='train',
calculate_prior_boxes=False,
backbone=None,
):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace, self).__init__()
self.phase = phase
# backbone = None
# if cfg['name'] == 'mobilenet0.25':
# backbone = MobileNetV1()
# if cfg['pretrain']:
# checkpoint = torch.load("./weights/mobilenetV1X0.25_pretrain.tar", map_location=torch.device('cpu'))
# from collections import OrderedDict
# new_state_dict = OrderedDict()
# for k, v in checkpoint['state_dict'].items():
# name = k[7:] # remove module.
# new_state_dict[name] = v
# # load params
# backbone.load_state_dict(new_state_dict)
# elif cfg['name'] == 'Resnet50':
# import torchvision.models as models
# backbone = models.resnet50(pretrained=cfg['pretrain'])
self.cfg = cfg
self.calculate_prior_boxes = calculate_prior_boxes
self.body = _utils.IntermediateLayerGetter(backbone,
cfg['return_layers'])
in_channels_stage2 = cfg['in_channel']
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list, out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(
fpn_num=3, inchannels=cfg['out_channel'])
def __init__(self, cfg = None, phase = 'train'):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace,self).__init__()
self.phase = phase
backbone = None
if cfg['name'] == 'mobilenet0.25':
backbone = MobileNetV1()
if cfg['pretrain']:
checkpoint = torch.load("./weights/mobilenetV1X0.25_pretrain.tar", map_location=torch.device('cpu'))
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in checkpoint['state_dict'].items():
name = k[7:] # remove module.
new_state_dict[name] = v
# load params
backbone.load_state_dict(new_state_dict)
elif cfg['name'] == 'Resnet50':
import torchvision.models as models
backbone = models.resnet50(pretrained=cfg['pretrain'])
elif cfg['name'] == 'detnas':
print('You were using DetNas as backbone, this is exprimental, may not work.')
self.backbone = ShuffleNetV2DetNAS(model_size='VOC_RetinaNet_300M')
detnas_pretrained = 'pretrained/VOC_RetinaNet_300M.pkl'
if os.path.exists(detnas_pretrained):
checkpoint = torch.load("VOC_RetinaNet_300M.pkl", map_location=torch.device('cpu'))
else:
print('{} does not exist, pls download it so that DetNas can be used. see readme under pretrained/')
exit(0)
self.backbone.load_state_dict(checkpoint)
self.backbone = self.backbone.features
return_layers = {'6': 1, '9': 2, '16': 3}
in_channels_stage2 = 80
self.body = _utils.IntermediateLayerGetter(backbone, cfg['return_layers'])
in_channels_stage2 = cfg['in_channel']
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list,out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3, inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=3, inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(fpn_num=3, inchannels=cfg['out_channel'])
def __init__(self, cfg=None, phase='train'):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace, self).__init__()
self.phase = phase
backbone = None
if cfg['name'] == 'mobilenet0.25':
backbone = MobileNetV1()
if cfg['pretrain']:
# 改成绝对路径
checkpoint = torch.load(os.path.join(
base_config.root_dir,
r"core\weights\retinaface\mobilenetV1X0.25_pretrain.tar"),
map_location=torch.device('cpu'))
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in checkpoint['state_dict'].items():
name = k[7:] # remove module.
new_state_dict[name] = v
# load params
backbone.load_state_dict(new_state_dict)
elif cfg['name'] == 'Resnet50':
import torchvision.models as models
backbone = models.resnet50(pretrained=cfg['pretrain'])
self.body = _utils.IntermediateLayerGetter(backbone,
cfg['return_layers'])
in_channels_stage2 = cfg['in_channel']
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list, out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(
fpn_num=3, inchannels=cfg['out_channel'])
def __init__(self, cfg=None, phase="train"):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace, self).__init__()
self.phase = phase
backbone = None
if cfg["name"] == "mobilenet0.25":
backbone = MobileNetV1()
if cfg["pretrain"]:
checkpoint = torch.load(
"./weights/mobilenetV1X0.25_pretrain.tar",
map_location=torch.device("cpu"),
)
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in checkpoint["state_dict"].items():
name = k[7:] # remove module.
new_state_dict[name] = v
# load params
backbone.load_state_dict(new_state_dict)
elif cfg["name"] == "Resnet50":
import torchvision.models as models
backbone = models.resnet50(pretrained=cfg["pretrain"])
self.body = _utils.IntermediateLayerGetter(backbone, cfg["return_layers"])
in_channels_stage2 = cfg["in_channel"]
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
out_channels = cfg["out_channel"]
self.fpn = FPN(in_channels_list, out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3, inchannels=cfg["out_channel"])
self.BboxHead = self._make_bbox_head(fpn_num=3, inchannels=cfg["out_channel"])
self.LandmarkHead = self._make_landmark_head(
fpn_num=3, inchannels=cfg["out_channel"]
)
def __init__(self, cfg=None, phase='train'):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace, self).__init__()
self.phase = phase
in_channels_list = self._make_body(cfg)
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list, out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(
fpn_num=3, inchannels=cfg['out_channel'])
def __init__(
self,
# cfg = None,
phase='train',
decode_boxes: bool = False,
backbone=None,
# Network Configuration
return_layers: Dict[str, int] = {
'stage1': '1',
'stage2': '2',
'stage3': '3'
},
in_channel: int = 32,
out_channel: int = 64,
min_sizes_list: List[Tuple[int, int]] = [(16, 32), (64, 128),
(256, 512)],
steps: List[int] = [8, 16, 32],
clip: bool = False,
image_size: Optional[Tuple[int, int]] = None,
# Decoding Configuration
variances: List[float] = [0.1, 0.2],
resize: int = 1,
confidence_threshold: float = 0.02,
nms_threshold: float = 0.4,
):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFaceModified, self).__init__()
self.phase = phase
# self.cfg = cfg
# Set config
self.decode_boxes = decode_boxes
self.min_sizes_list = min_sizes_list
self.steps = steps
self.clip = clip
self.image_size = image_size
self.variances = variances
self.resize = resize
self.confidence_threshold = confidence_threshold
self.nms_threshold = nms_threshold
if self.image_size is not None:
self.prior_boxes = prior_box(
torch.tensor(self.image_size).float(), self.min_sizes_list,
self.steps, self.clip)
else:
self.prior_boxes = None
self.body = _utils.IntermediateLayerGetter(backbone, return_layers)
in_channels_stage2 = in_channel
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
out_channels = out_channel
self.fpn = FPN(in_channels_list, out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3,
inchannels=out_channel)
self.BboxHead = self._make_bbox_head(fpn_num=3, inchannels=out_channel)
self.LandmarkHead = self._make_landmark_head(fpn_num=3,
inchannels=out_channel)
def __init__(self, cfg=None, phase='train'):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace, self).__init__()
self.phase = phase
backbone = None
if cfg['name'] == 'mobilenet0.25':
backbone = MobileNetV1()
if cfg['pretrain']:
checkpoint = torch.load(
"./weights/mobilenetV1X0.25_pretrain.tar",
map_location=torch.device('cpu'))
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in checkpoint['state_dict'].items():
name = k[7:] # remove module.
new_state_dict[name] = v
# load params
backbone.load_state_dict(new_state_dict)
self.body = _utils.IntermediateLayerGetter(backbone,
cfg['return_layers'])
in_channels_stage2 = cfg['in_channel']
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
elif cfg['name'] == 'Resnet50':
import torchvision.models as models
backbone = models.resnet50(pretrained=cfg['pretrain'])
self.body = _utils.IntermediateLayerGetter(backbone,
cfg['return_layers'])
in_channels_stage2 = cfg['in_channel']
in_channels_list = [
in_channels_stage2 * 2,
in_channels_stage2 * 4,
in_channels_stage2 * 8,
]
elif cfg['name'] == 'selecsls60':
self.body = timm.create_model('selecsls60',
features_only=True,
out_indices=(cfg['return_layers']),
pretrained=cfg['pretrain'])
in_channels_list = self.body.feature_info.channels()
elif cfg['name'] == 'mobilenetv3_large_100':
self.body = timm.create_model('mobilenetv3_large_100',
features_only=True,
out_indices=(cfg['return_layers']),
pretrained=cfg['pretrain'])
in_channels_list = self.body.feature_info.channels()
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list, out_channels)
self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=3,
inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(
fpn_num=3, inchannels=cfg['out_channel'])
def __init__(self, cfg = None, phase = 'train'):
"""
:param cfg: Network related settings.
:param phase: train or test.
"""
super(RetinaFace,self).__init__()
self.phase = phase
backbone = None
if cfg['name'] == 'mobilenet0.25':
backbone = MobileNetV1()
if cfg['pretrain']:
checkpoint = torch.load("./weights/mobilenetV1X0.25_pretrain.tar", map_location=torch.device('cpu'))
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in checkpoint['state_dict'].items():
name = k[7:] # remove module.
new_state_dict[name] = v
# load params
backbone.load_state_dict(new_state_dict)
elif cfg['name'] == 'Resnet50':
import torchvision.models as models
backbone = models.resnet50(pretrained=cfg['pretrain'])
elif cfg['name'] == 'mobilenetv3':
backbone = MobileNetV3()
# print(backbone)
if cfg['pretrain']:
checkpoint = torch.load("./weights/mobilenetv3.pth", map_location=torch.device('cpu'))
print("Pretrained Weights : ",type(checkpoint))
backbone.load_state_dict(checkpoint)
elif cfg['name'] == 'mobilenetv2_0.1':
backbone = MobileNetV2()
if cfg['pretrain']:
checkpoint = torch.load("./weights/mobilenetv2_0.1_face.pth", map_location=torch.device('cpu'))
backbone.load_state_dict(checkpoint)
elif cfg['name'] == 'efficientnetb0':
backbone = EfficientNet.from_name("efficientnet-b0")
if cfg['pretrain']:
checkpoint = torch.load("./weights/efficientnetb0_face.pth", map_location=torch.device('cpu'))
backbone.load_state_dict(checkpoint)
print("succeed loaded weights...")
self.body = _utils.IntermediateLayerGetter(backbone, cfg['return_layers'])
if cfg['name'] == 'mobilenet0.25':
in_channels_stage2 = cfg['in_channel']
in_channels_list = [
# in_channels_stage2 * 2,
in_channels_stage2*4,
in_channels_stage2*8,
]
elif cfg['name'] == 'mobilenetv2_0.1':
in_channels_stage2 = cfg['in_channel1']
in_channels_stage3 = cfg['in_channel2']
in_channels_list = [
# in_channels_stage2 * 2,
in_channels_stage2,
in_channels_stage3,
]
elif cfg['name'] == 'mobilenetv3':
in_channels_stage2 = cfg['in_channel1']
in_channels_stage3 = cfg['in_channel2']
in_channels_list = [
# in_channels_stage2 * 2,
in_channels_stage2,
in_channels_stage3,
]
elif cfg['name'] == 'efficientnetb0':
in_channels_stage2 = cfg['in_channel1']
in_channels_stage3 = cfg['in_channel2']
in_channels_list = [
# in_channels_stage2 * 2,
in_channels_stage2,
in_channels_stage3,
]
out_channels = cfg['out_channel']
self.fpn = FPN(in_channels_list,out_channels)
# self.ssh1 = SSH(out_channels, out_channels)
self.ssh2 = SSH(out_channels, out_channels)
self.ssh3 = SSH(out_channels, out_channels)
self.ClassHead = self._make_class_head(fpn_num=2, inchannels=cfg['out_channel'])
self.BboxHead = self._make_bbox_head(fpn_num=2, inchannels=cfg['out_channel'])
self.LandmarkHead = self._make_landmark_head(fpn_num=2, inchannels=cfg['out_channel'])