def _construct_class()

in pycls/models/efficientnet.py [0:0]

• 34 lines of code
• 9 McCabe index (conditional complexity)

    def _construct_class(self, in_w, exp_r, kernel, stride, se_r, out_w, act_fun):
        # Expansion: 1x1, BN, Swish
        self.expand = None
        exp_w = int(in_w * exp_r)
        # Include exp ops only if the exp ratio is different from 1
        if exp_w != in_w:
            self.expand = nn.Conv2d(
                in_w, exp_w,
                kernel_size=1, stride=1, padding=0, bias=False
            )
            self.expand_bn = nn.BatchNorm2d(
                exp_w, eps=cfg.BN.EPS, momentum=cfg.BN.MOM
            )
            self.expand_swish = act_fun()
        # Depthwise: 3x3 dwise, BN, Swish
        self.dwise = nn.Conv2d(
            exp_w, exp_w,
            kernel_size=kernel, stride=stride, groups=exp_w, bias=False,
            # Hacky padding to preserve res  (supports only 3x3 and 5x5)
            padding=(1 if kernel == 3 else 2)
        )
        self.dwise_bn = nn.BatchNorm2d(
            exp_w, eps=cfg.BN.EPS, momentum=cfg.BN.MOM
        )
        self.dwise_swish = act_fun()
        # SE: x * F_ex(x)
        if cfg.EFFICIENT_NET.SE_ENABLED:
            se_w = int(in_w * se_r)
            self.se = SE(exp_w, se_w, act_fun)
        # Linear projection: 1x1, BN
        self.lin_proj = nn.Conv2d(
            exp_w, out_w,
            kernel_size=1, stride=1, padding=0, bias=False
        )
        self.lin_proj_bn = nn.BatchNorm2d(
            out_w, eps=cfg.BN.EPS, momentum=cfg.BN.MOM
        )
        # Nonlinear projection
        if not cfg.EFFICIENT_NET.LIN_PROJ:
            self.lin_proj_swish = act_fun()
        # Skip connections on blocks w/ same in and out shapes (MN-V2, Fig. 4)
        self.has_skip = (stride == 1) and (in_w == out_w)