def __init__(self):
super().__init__()
self.backbone = construct_backbone(cfg.backbone)
if cfg.freeze_bn:
self.freeze_bn()
in_channels = cfg.fpn.num_features # 256
self.proto_net, cfg.coef_dim = make_net(in_channels,
cfg.mask_proto_net,
include_last_relu=False)
'''
self.proto_net:
Sequential((0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace)
(2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace)
(4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(5): ReLU(inplace)
(6): InterpolateModule()
(7): ReLU(inplace)
(8): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(9): ReLU(inplace)
(10): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1)))
cfg.coef_dim: 32
'''
self.fpn = FPN([512, 1024, 2048])
self.selected_layers = [0, 1, 2, 3, 4]
# create a ModuleList to match with the original pre-trained weights (original model state_dict)
self.prediction_layers = nn.ModuleList()
self.prediction_layers.append(PredictionModule(in_channels))
'''
self.prediction_layers:
ModuleList(
(0): PredictionModule((upfeature): Sequential((0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace))
(bbox_layer): Conv2d(256, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conf_layer): Conv2d(256, 243, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(mask_layer): Conv2d(256, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))))
'''
if cfg.train_semantic: # True
self.semantic_seg_conv = nn.Conv2d(256,
cfg.num_classes - 1,
kernel_size=1)
self.anchors = []
for i, hw in enumerate(cfg.hws):
self.anchors += make_anchors(hw[1], hw[0], cfg.backbone.scales[i])
self.anchors = torch.Tensor(self.anchors).view(-1, 4).cuda()
def __init__(self, cfg):
super().__init__()
self.cfg = cfg
self.anchors = []
self.backbone = construct_backbone(cfg.__class__.__name__, (1, 2, 3))
self.proto_net, coef_dim = make_net(256, mask_proto_net, include_last_relu=False)
self.fpn = FPN([512, 1024, 2048])
# create a ModuleList to match with the original pre-trained weights (original model state_dict)
self.prediction_layers = nn.ModuleList()
self.prediction_layers.append(PredictionModule(cfg, coef_dim=coef_dim))
if cfg.mode == 'train':
self.semantic_seg_conv = nn.Conv2d(256, cfg.num_classes - 1, kernel_size=1)
def __init__(self, cfg):
super().__init__()
self.cfg = cfg
self.anchors = []
self.backbone = construct_backbone(cfg.__class__.__name__, (1, 2, 3))
self.proto_net, coef_dim = make_net(256,
mask_proto_net,
include_last_relu=False)
self.fpn = FPN([512, 1024, 2048])
self.prediction_layers = nn.ModuleList()
self.prediction_layers.append(PredictionModule(cfg, coef_dim=coef_dim))
if cfg.mode == 'train':
ch_out = cfg.num_classes - 1
self.semantic_seg_conv = nn.Conv2d(256, ch_out, kernel_size=1)
def __init__(self, cfg):
super().__init__()
self.cfg = cfg
self.anchors = []
self.backbone = construct_backbone(cfg.__class__.__name__, (1, 2, 3))
if cfg.mode == 'train' and cfg.freeze_bn:
self.freeze_bn()
self.proto_net, coef_dim = make_net(256,
mask_proto_net,
include_last_relu=False)
'''
self.proto_net:
Sequential((0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace)
(2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace)
(4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(5): ReLU(inplace)
(6): InterpolateModule()
(7): ReLU(inplace)
(8): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(9): ReLU(inplace)
(10): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1)))
'''
self.fpn = FPN([512, 1024, 2048])
# create a ModuleList to match with the original pre-trained weights (original model state_dict)
self.prediction_layers = nn.ModuleList()
self.prediction_layers.append(PredictionModule(cfg, coef_dim=coef_dim))
'''
self.prediction_layers:
ModuleList(
(0): PredictionModule((upfeature): Sequential((0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace))
(bbox_layer): Conv2d(256, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conf_layer): Conv2d(256, 243, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(mask_layer): Conv2d(256, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))))
'''
if cfg.mode == 'train' and cfg.train_semantic: # True
self.semantic_seg_conv = nn.Conv2d(256,
cfg.num_classes - 1,
kernel_size=1)