def __init__()

in src/baselines/dnn.py [0:0]


    def __init__(self, config, args):
        super(DNN, self).__init__()
        self.config = config
        self.num_labels = config.num_labels
        self.output_mode = args.output_mode
        if config.activate_func == "tanh":
            self.activate = nn.Tanh()
        elif config.activate_func == "relu":
            self.activate = nn.ReLU()
        elif config.activate_func == "gelu":
            self.activate = nn.GELU()
        elif config.activate_func == "leakyrelu":
            self.activate = nn.LeakyReLU()
        else:
            self.activate = nn.Tanh()
        self.dropout = nn.Dropout(config.dropout)
        layers = []
        cur_input_dim = config.input_dim
        for idx in range(len(config.hidden_dim_list)):
            cur_output_dim = config.hidden_dim_list[idx]
            layer = nn.Linear(in_features=cur_input_dim, out_features=cur_output_dim, bias=config.bias)
            cur_input_dim = cur_output_dim
            layers.append(layer)
            layers.append(self.dropout)
            layers.append(self.activate)
        output_dim = config.num_labels
        if output_dim == 2:
            output_dim = 1
        layer = nn.Linear(in_features=cur_input_dim, out_features=output_dim, bias=config.bias)
        layers.append(layer)

        self.layers = nn.ModuleList(layers)

        if args.sigmoid:
            self.output = nn.Sigmoid()
        else:
            if self.num_labels > 1:
                self.output = nn.Softmax(dim=1)

            else:
                self.output = None
        # self.net = nn.Sequential(*layers)

        self.loss_type = args.loss_type

        # weight for the loss function
        if hasattr(config, "pos_weight"):
            self.pos_weight = config.pos_weight
        elif hasattr(args, "pos_weight"):
            self.pos_weight = args.pos_weight
        else:
            self.pos_weight = None

        if hasattr(config, "weight"):
            self.weight = config.weight
        elif hasattr(args, "weight"):
            self.weight = args.weight
        else:
            self.weight = None

        if self.output_mode in ["regression"]:
            self.loss_fct = MSELoss()
        elif self.output_mode in ["multi_label", "multi-label"]:
            if self.loss_type == "bce":
                if self.pos_weight:
                    # [1, 1, 1, ,1, 1...] length: self.num_labels
                    assert self.pos_weight.ndim == 1 and self.pos_weight.shape[0] == self.num_labels
                    self.loss_fct = BCEWithLogitsLoss(pos_weight=self.pos_weight)
                else:
                    self.loss_fct = BCEWithLogitsLoss(reduction=config.loss_reduction if hasattr(config, "loss_reduction") else "sum")
            elif self.loss_type == "asl":
                self.loss_fct = AsymmetricLossOptimized(gamma_neg=args.asl_gamma_neg if hasattr(args, "asl_gamma_neg") else 4,
                                                        gamma_pos=args.asl_gamma_pos if hasattr(args, "asl_gamma_pos") else 1,
                                                        clip=args.clip if hasattr(args, "clip") else 0.05,
                                                        eps=args.eps if hasattr(args, "eps") else 1e-8,
                                                        disable_torch_grad_focal_loss=args.disable_torch_grad_focal_loss if hasattr(args, "disable_torch_grad_focal_loss") else False)
            elif self.loss_type == "focal_loss":
                self.loss_fct = FocalLoss(alpha=args.focal_loss_alpha if hasattr(args, "focal_loss_alpha") else 1,
                                          gamma=args.focal_loss_gamma if hasattr(args, "focal_loss_gamma") else 0.25,
                                          normalization=False,
                                          reduce=args.focal_loss_reduce if hasattr(args, "focal_loss_reduce") else False)
            elif self.loss_type == "multilabel_cce":
                self.loss_fct = MultiLabel_CCE(normalization=False)
        elif self.output_mode in ["binary_class", "binary-class"]:
            if self.loss_type == "bce":
                if self.pos_weight:
                    # [0.9]
                    if isinstance(self.pos_weight, int):
                        self.pos_weight = torch.tensor([self.pos_weight], dtype=torch.long).to(args.device)
                    elif isinstance(self.pos_weight, float):
                        self.pos_weight = torch.tensor([self.pos_weight], dtype=torch.float32).to(args.device)
                    assert self.pos_weight.ndim == 1 and self.pos_weight.shape[0] == 1
                    self.loss_fct = BCEWithLogitsLoss(pos_weight=self.pos_weight)
                else:
                    self.loss_fct = BCEWithLogitsLoss()
            elif self.loss_type == "focal_loss":
                self.loss_fct = FocalLoss(alpha=args.focal_loss_alpha if hasattr(args, "focal_loss_alpha") else 1,
                                          gamma=args.focal_loss_gamma if hasattr(args, "focal_loss_gamma") else 0.25,
                                          normalization=False,
                                          reduce=args.focal_loss_reduce if hasattr(args, "focal_loss_reduce") else False)
        elif self.output_mode in ["multi_class", "multi-class"]:
            if self.weight:
                # [1, 1, 1, ,1, 1...] length: self.num_labels
                assert self.weight.ndim == 1 and self.weight.shape[0] == self.num_labels
                self.loss_fct = CrossEntropyLoss(weight=self.weight)
            else:
                self.loss_fct = CrossEntropyLoss()
        else:
            raise Exception("Not support output mode: %s." % self.output_mode)