def __init__(self, device, input_size=None, num_classes=2, trainable=False, conf_thresh=0.05, nms_thresh=0.2, anchor_size=None, hr=False):
super(YOLOv2slim, self).__init__()
self.device = device
self.input_size = input_size
self.num_classes = num_classes
self.trainable = trainable
self.conf_thresh = conf_thresh
self.nms_thresh = nms_thresh
self.anchor_size = torch.tensor(anchor_size)
self.anchor_number = len(anchor_size)
self.stride = 32
self.grid_cell, self.all_anchor_wh = self.create_grid(input_size)
self.scale = np.array([[[input_size[1], input_size[0], input_size[1], input_size[0]]]])
self.scale_torch = torch.tensor(self.scale.copy(), device=device).float()
# backbone darknet-tiny
self.backbone = darknet_tiny(pretrained=trainable, hr=hr)
# detection head
self.convsets_1 = nn.Sequential(
SPP(),
Conv2d(512*4, 256, 1, leakyReLU=True),
Conv2d(256, 512, 3, 1, leakyReLU=True)
)
self.route_layer = Conv2d(256, 32, 1, leakyReLU=True)
self.reorg = reorg_layer(stride=2)
self.convsets_2 = Conv2d(640, 512, 3, 1, leakyReLU=True)
# prediction layer
self.pred_ = nn.Conv2d(512, self.anchor_number*(1 + 4 + self.num_classes), 1)
def __init__(self,
device,
input_size=None,
num_classes=20,
trainable=False,
conf_thresh=0.001,
nms_thresh=0.5,
anchor_size=None,
hr=False):
super(myYOLOv2, self).__init__()
self.device = device
self.input_size = input_size
self.num_classes = num_classes
self.trainable = trainable
self.conf_thresh = conf_thresh
self.nms_thresh = nms_thresh
self.anchor_size = torch.tensor(anchor_size)
self.anchor_number = len(anchor_size)
self.stride = 32
self.grid_cell, self.all_anchor_wh = self.create_grid()
self.scale = np.array(
[[input_size[1], input_size[0], input_size[1], input_size[0]]])
self.scale_torch = torch.tensor(self.scale.copy(),
device=device).float()
# backbone darknet-19
self.backbone = darknet19(pretrained=trainable, hr=hr)
# detection head
self.convsets_1 = nn.Sequential(
Conv2d(1024, 1024, 3, 1, leakyReLU=True),
Conv2d(1024, 1024, 3, 1, leakyReLU=True))
# self.route_alyer = nn.Sequential(
# Conv2d(512, 64, 1, leakyReLU=True),
# Conv2d(64, 256, 3, padding=1, stride=2, leakyReLU=True)
# )
self.route_layer = Conv2d(512, 64, 1, leakyReLU=True)
self.reorg = reorg_layer(stride=2)
self.convsets_2 = Conv2d(1280, 1024, 3, 1, leakyReLU=True)
# prediction layer
self.pred = nn.Conv2d(1024,
self.anchor_number * (1 + 4 + self.num_classes),
1)
def __init__(self,
device,
input_size=None,
num_classes=20,
trainable=False,
conf_thresh=0.001,
nms_thresh=0.6,
anchor_size=None):
super(YOLOv2R50, self).__init__()
self.device = device
self.input_size = input_size
self.num_classes = num_classes
self.trainable = trainable
self.conf_thresh = conf_thresh
self.nms_thresh = nms_thresh
self.anchor_size = torch.tensor(anchor_size)
self.num_anchors = len(anchor_size)
self.stride = 32
self.grid_cell, self.all_anchor_wh = self.create_grid(input_size)
# 主干网络：resnet50
self.backbone = resnet50(pretrained=trainable)
# 检测头
self.convsets_1 = nn.Sequential(Conv(2048, 1024, k=1),
Conv(1024, 1024, k=3, p=1),
Conv(1024, 1024, k=3, p=1))
# 融合高分辨率的特征信息
self.route_layer = Conv(1024, 128, k=1)
self.reorg = reorg_layer(stride=2)
# 检测头
self.convsets_2 = Conv(1024 + 128 * 4, 1024, k=3, p=1)
# 预测曾
self.pred = nn.Conv2d(1024,
self.num_anchors * (1 + 4 + self.num_classes), 1)
def __init__(self,
device,
input_size=None,
num_classes=20,
trainable=False,
conf_thresh=0.001,
nms_thresh=0.5,
anchor_size=None,
hr=False):
super(YOLOv2D19, self).__init__()
self.device = device
self.input_size = input_size
self.num_classes = num_classes
self.trainable = trainable
self.conf_thresh = conf_thresh
self.nms_thresh = nms_thresh
self.anchor_size = torch.tensor(anchor_size)
self.num_anchors = len(anchor_size)
self.stride = 32
self.grid_cell, self.all_anchor_wh = self.create_grid(input_size)
# backbone darknet-19
self.backbone = darknet19(pretrained=trainable, hr=hr)
# detection head
self.convsets_1 = nn.Sequential(Conv(1024, 1024, k=3, p=1),
Conv(1024, 1024, k=3, p=1))
self.route_layer = Conv(512, 64, k=1)
self.reorg = reorg_layer(stride=2)
self.convsets_2 = Conv(1280, 1024, k=3, p=1)
# prediction layer
self.pred = nn.Conv2d(1024,
self.num_anchors * (1 + 4 + self.num_classes),
kernel_size=1)