def __init__(self, num_anchors=9, num_classes=20, compound_coef=0):
super(EfficientDet, self).__init__()
self.compound_coef = compound_coef
self.num_channels = [64, 88, 112, 160, 224, 288, 384, 384][self.compound_coef]
self.conv3 = nn.Conv2d(48, self.num_channels, kernel_size=1, stride=1, padding=0)#40
self.conv4 = nn.Conv2d(96, self.num_channels, kernel_size=1, stride=1, padding=0)#80
self.conv5 = nn.Conv2d(232, self.num_channels, kernel_size=1, stride=1, padding=0)#192
self.conv6 = nn.Conv2d(232, self.num_channels, kernel_size=3, stride=2, padding=1)#192
self.conv7 = nn.Sequential(nn.ReLU(),
nn.Conv2d(self.num_channels, self.num_channels, kernel_size=3, stride=2, padding=1))
self.bifpn = nn.Sequential(*[BiFPN(self.num_channels) for _ in range(min(2 + self.compound_coef, 8))])
self.num_classes = num_classes
self.regressor = Regressor(in_channels=self.num_channels, num_anchors=num_anchors,
num_layers=3 + self.compound_coef // 3)
self.classifier = Classifier(in_channels=self.num_channels, num_anchors=num_anchors, num_classes=num_classes,
num_layers=3 + self.compound_coef // 3)
self.anchors = Anchors()
self.regressBoxes = BBoxTransform()
self.clipBoxes = ClipBoxes()
self.focalLoss = FocalLoss()
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
prior = 0.01
self.classifier.header.weight.data.fill_(0)
self.classifier.header.bias.data.fill_(-math.log((1.0 - prior) / prior))
self.regressor.header.weight.data.fill_(0)
self.regressor.header.bias.data.fill_(0)
self.backbone_net = EfficientNet()
def __init__(self, config):
super(EfficientDet, self).__init__()
self.is_training = config.is_training
self.nms_threshold = config.nms_threshold
model_conf = EFFICIENTDET[config.network]
self.num_channels = model_conf['W_bifpn']
input_channels = model_conf['EfficientNet_output']
self.convs = []
self.conv3 = nn.Conv2d(input_channels[0],
self.num_channels,
kernel_size=1,
stride=1,
padding=0)
self.conv4 = nn.Conv2d(input_channels[1],
self.num_channels,
kernel_size=1,
stride=1,
padding=0)
self.conv5 = nn.Conv2d(input_channels[2],
self.num_channels,
kernel_size=1,
stride=1,
padding=0)
self.conv6 = nn.Conv2d(input_channels[3],
self.num_channels,
kernel_size=1,
stride=1,
padding=0)
self.conv7 = nn.Conv2d(input_channels[4],
self.num_channels,
kernel_size=1,
stride=1,
padding=0)
self.convs.append(self.conv3)
self.convs.append(self.conv4)
self.convs.append(self.conv5)
self.convs.append(self.conv6)
self.convs.append(self.conv7)
self.bifpn = nn.Sequential(
*[BiFPN(self.num_channels) for _ in range(model_conf['D_bifpn'])])
self.num_classes = config.num_classes
self.anchors = Anchors()
self.regressor = Regressor(in_channels=self.num_channels,
num_anchors=self.anchors.num_anchors,
num_layers=model_conf['D_class'])
self.classifier = Classifier(in_channels=self.num_channels,
num_anchors=self.anchors.num_anchors,
num_classes=self.num_classes,
num_layers=model_conf['D_class'])
self.regressBoxes = BBoxTransform()
self.clipBoxes = ClipBoxes()
self.focalLoss = FocalLoss()
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
prior = 0.01
self.classifier.header.weight.data.fill_(0)
self.classifier.header.bias.data.fill_(-math.log((1.0 - prior) /
prior))
self.regressor.header.weight.data.fill_(0)
self.regressor.header.bias.data.fill_(0)
if config.resume:
self.backbone_net = EfficientNet.from_name(
model_conf['EfficientNet'])
else:
self.backbone_net = EfficientNet.from_pretrained(
model_conf['EfficientNet'])