def __init__(self,
num_classes,
levels=3,
num_channels=128,
model_name='efficientdet-d0',
is_training=True,
threshold=0.5):
super(EfficientDet, self).__init__()
self.efficientnet = EfficientNet.from_pretrained(MODEL_MAP[model_name])
self.is_training = is_training
self.BIFPN = BIFPN(in_channels=self.efficientnet.get_list_features()[2:],
out_channels=256,
num_outs=5)
self.regressionModel = RegressionModel(256)
self.classificationModel = ClassificationModel(256, num_classes=num_classes)
self.anchors = Anchors()
self.regressBoxes = BBoxTransform()
self.clipBoxes = ClipBoxes()
self.threshold = threshold
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.classificationModel.output.weight.data.fill_(0)
self.classificationModel.output.bias.data.fill_(-math.log((1.0-prior)/prior))
self.regressionModel.output.weight.data.fill_(0)
self.regressionModel.output.bias.data.fill_(0)
self.freeze_bn()
def __init__(self,
num_classes,
network='efficientdet-d0',
D_bifpn=3,
W_bifpn=88,
D_class=3,
is_training=True,
threshold=0.5,
iou_threshold=0.5,
gpu=1):
super(EfficientDet, self).__init__()
self.backbone = EfficientNet.from_pretrained(MODEL_MAP[network])
self.is_training = is_training
self.neck = BIFPN(in_channels=self.backbone.get_list_features()[-5:],
out_channels=W_bifpn,
stack=D_bifpn,
num_outs=5)
self.bbox_head = RetinaHead(num_classes=num_classes,
in_channels=W_bifpn)
self.anchors = Anchors()
self.regressBoxes = BBoxTransform()
self.clipBoxes = ClipBoxes()
self.threshold = threshold
self.iou_threshold = iou_threshold
self.gpu = gpu
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_()
self.freeze_bn()
self.criterion = FocalLoss()
def detection(classification, regression, inputs, score_thresh=0.01, iou_thresh=0.5):
anchors = Anchors()
anchors = anchors(inputs)
regressBoxes = BBoxTransform()
clipBoxes = ClipBoxes()
transformed_anchors = regressBoxes(anchors, regression)
transformed_anchors = clipBoxes(transformed_anchors, inputs)
scores = torch.max(classification, dim=2, keepdim=True)[0]
over_score_thresh_idx = (scores > score_thresh)[0, :, 0]
classfiy_over_thresh = classification[:, over_score_thresh_idx, :]
anchors_over_thresh = transformed_anchors[:, over_score_thresh_idx, :]
scores_over_thresh = scores[:, over_score_thresh_idx, :]
# nms
score = scores_over_thresh[0, :, :]
anchors_score = torch.cat([anchors_over_thresh[0, :, :], score], dim=1)
anchors_nms_idx, _ = soft_nms(anchors_score, score_threshold=iou_thresh)
nms_scores, nms_class = classfiy_over_thresh[0, anchors_nms_idx, :].max(
dim=1)
nms_anchors = anchors_over_thresh[0, anchors_nms_idx, :]
return [nms_scores, nms_class, nms_anchors]
def __init__(self,
num_classes,
network='efficientdet-d0',
D_bifpn=3,
W_bifpn=88):
super(EfficientDetBiFPN, self).__init__()
self.backbone = EfficientNet.get_network_from_name(MODEL_MAP[network])
self.neck = BIFPN(in_channels=self.backbone.get_list_features()[-5:],
out_channels=W_bifpn,
stack=D_bifpn,
num_outs=5)
self.bbox_head = RetinaHead(num_classes=num_classes,
in_channels=W_bifpn)
self.anchors = Anchors()
self.regressBoxes = BBoxTransform()
self.clipBoxes = ClipBoxes()
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_()
self.freeze_bn()
def __init__(self,
num_classes=21,
levels=3,
num_channels=128,
model_name='efficientnet-b0',
is_training=True):
super(EfficientDet, self).__init__()
self.efficientnet = EfficientNet.from_pretrained(model_name)
self.is_training = is_training
self.BIFPN = BIFPN(in_channels=[40, 80, 112, 192, 320],
out_channels=256,
num_outs=5)
self.regressionModel = RegressionModel(256)
self.classificationModel = ClassificationModel(256,
num_classes=num_classes)
self.anchors = Anchors()
self.regressBoxes = BBoxTransform()
self.clipBoxes = ClipBoxes()
def __init__(self,
num_classes,
network='efficientdet-d0',
D_bifpn=3,
W_bifpn=88,
D_class=3,
is_training=True,
threshold=0.01,
iou_threshold=0.5):
super(EfficientDet, self).__init__()
# self.backbone = EfficientNet.from_pretrained(MODEL_MAP[network])
self.backbone = EfficientNet.get_network_from_name(MODEL_MAP[network])
# print backbone parameters
# params = list(self.backbone.named_parameters())
# for param_key, param_value in params:
# print("{}, {}".format(param_key, param_value.shape))
#
# for features in self.backbone.get_list_features():
# print(features)
self.is_training = is_training
self.neck = BIFPN(in_channels=self.backbone.get_list_features()[-5:],
out_channels=W_bifpn,
stack=D_bifpn,
num_outs=5)
self.bbox_head = RetinaHead(num_classes=num_classes,
in_channels=W_bifpn)
self.anchors = Anchors()
self.regressBoxes = BBoxTransform()
self.clipBoxes = ClipBoxes()
self.threshold = threshold
self.iou_threshold = iou_threshold
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_()
self.freeze_bn()
self.criterion = FocalLoss()
def __init__(self,
num_classes,
network='efficientdet-d0',
D_bifpn=3,
W_bifpn=88,
D_class=3,
is_training=True,
threshold=0.5,
iou_threshold=0.5):
super(EfficientDet, self).__init__()
# self.efficientnet = EfficientNet.from_pretrained(MODEL_MAP[network])
self.efficientnet = EfficientNet.from_name(
MODEL_MAP[network], override_params={'num_classes': num_classes})
self.is_training = is_training
self.BIFPN = BIFPN(
in_channels=self.efficientnet.get_list_features()[-5:],
out_channels=W_bifpn,
stack=D_bifpn,
num_outs=5)
self.regressionModel = RegressionModel(W_bifpn)
self.classificationModel = ClassificationModel(W_bifpn,
num_classes=num_classes)
self.anchors = Anchors()
self.regressBoxes = BBoxTransform()
self.clipBoxes = ClipBoxes()
self.threshold = threshold
self.iou_threshold = iou_threshold
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.classificationModel.output.weight.data.fill_(0)
self.classificationModel.output.bias.data.fill_(-math.log(
(1.0 - prior) / prior))
self.regressionModel.output.weight.data.fill_(0)
self.regressionModel.output.bias.data.fill_(0)
self.freeze_bn()