示例#1
0
    def __init__(self, cfg):
        super().__init__()

        self.in_features = cfg.MODEL.FCOS.IN_FEATURES

        # Loss parameters:
        # defined by method<get_ground_truth>
        self.num_points_per_level = None
        self.fpn_strides = cfg.MODEL.FCOS.FPN_STRIDES
        self.center_sampling_radius = cfg.MODEL.FCOS.CENTER_SAMPLING_RADIUS
        self.norm_reg_targets = cfg.MODEL.FCOS.NORM_REG_TARGETS

        self.focal_loss_alpha = cfg.MODEL.FCOS.FOCAL_LOSS_ALPHA
        self.focal_loss_gamma = cfg.MODEL.FCOS.FOCAL_LOSS_GAMMA
        self.iou_loss_type = cfg.MODEL.FCOS.IOU_LOSS_TYPE

        # Inference parameters:
        self.score_thresh = 0.3
        self.pre_nms_thresh = cfg.MODEL.FCOS.INFERENCE_TH
        self.pre_nms_top_n = cfg.MODEL.FCOS.PRE_NMS_TOP_N
        self.nms_thresh = cfg.MODEL.FCOS.NMS_TH
        self.max_detections_per_image = cfg.TEST.DETECTIONS_PER_IMAGE
        self.min_size = 0
        self.num_classes = cfg.MODEL.FCOS.NUM_CLASSES

        self.backbone = build_backbone(cfg)

        backbone_shape = self.backbone.output_shape()
        feature_shapes = [backbone_shape[f] for f in self.in_features]
        self.head = FCOSHead(cfg, feature_shapes)

        self.register_buffer("pixel_mean",
                             torch.Tensor(cfg.MODEL.PIXEL_MEAN).view(-1, 1, 1))
        self.register_buffer("pixel_std",
                             torch.Tensor(cfg.MODEL.PIXEL_STD).view(-1, 1, 1))
示例#2
0
def test_backbone():
    backbone = build_backbone(cfg).to(device)
    images = torch.empty((2, 3, 512, 512)).to(device)
    assert isinstance(backbone, nn.Module)

    outputs = backbone(images)

    ipdb.set_trace()
示例#3
0
def test_backbone():
    backbone = build_backbone(cfg).to(device)
    images = torch.empty((2, 3, 512, 512)).to(device)
    assert isinstance(backbone, nn.Module)

    num = 0
    for module in backbone.modules():
        if isinstance(module, nn.Conv2d):
            num += 1

    print(num)
    outputs = backbone(images)

    import pdb
    pdb.set_trace()