def __init__()

in src/controlnet_aux/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py [0:0]


    def __init__(self, core,  bin_conf, bin_centers_type="softplus", bin_embedding_dim=128,
                 n_attractors=[16, 8, 4, 1], attractor_alpha=300, attractor_gamma=2, attractor_kind='sum', attractor_type='exp',
                 min_temp=5, max_temp=50,
                 memory_efficient=False, train_midas=True,
                 is_midas_pretrained=True, midas_lr_factor=1, encoder_lr_factor=10, pos_enc_lr_factor=10, inverse_midas=False,  **kwargs):
        """ZoeDepthNK model. This is the version of ZoeDepth that has two metric heads and uses a learned router to route to experts.

        Args:
            core (models.base_models.midas.MidasCore): The base midas model that is used for extraction of "relative" features

            bin_conf (List[dict]): A list of dictionaries that contain the bin configuration for each metric head. Each dictionary should contain the following keys: 
                                    "name" (str, typically same as the dataset name), "n_bins" (int), "min_depth" (float), "max_depth" (float)

                                   The length of this list determines the number of metric heads.
            bin_centers_type (str, optional): "normed" or "softplus". Activation type used for bin centers. For "normed" bin centers, linear normalization trick is applied. This results in bounded bin centers.
                                               For "softplus", softplus activation is used and thus are unbounded. Defaults to "normed".
            bin_embedding_dim (int, optional): bin embedding dimension. Defaults to 128.

            n_attractors (List[int], optional): Number of bin attractors at decoder layers. Defaults to [16, 8, 4, 1].
            attractor_alpha (int, optional): Proportional attractor strength. Refer to models.layers.attractor for more details. Defaults to 300.
            attractor_gamma (int, optional): Exponential attractor strength. Refer to models.layers.attractor for more details. Defaults to 2.
            attractor_kind (str, optional): Attraction aggregation "sum" or "mean". Defaults to 'sum'.
            attractor_type (str, optional): Type of attractor to use; "inv" (Inverse attractor) or "exp" (Exponential attractor). Defaults to 'exp'.

            min_temp (int, optional): Lower bound for temperature of output probability distribution. Defaults to 5.
            max_temp (int, optional): Upper bound for temperature of output probability distribution. Defaults to 50.
            
            memory_efficient (bool, optional): Whether to use memory efficient version of attractor layers. Memory efficient version is slower but is recommended incase of multiple metric heads in order save GPU memory. Defaults to False.

            train_midas (bool, optional): Whether to train "core", the base midas model. Defaults to True.
            is_midas_pretrained (bool, optional): Is "core" pretrained? Defaults to True.
            midas_lr_factor (int, optional): Learning rate reduction factor for base midas model except its encoder and positional encodings. Defaults to 10.
            encoder_lr_factor (int, optional): Learning rate reduction factor for the encoder in midas model. Defaults to 10.
            pos_enc_lr_factor (int, optional): Learning rate reduction factor for positional encodings in the base midas model. Defaults to 10.

        """

        super().__init__()

        self.core = core
        self.bin_conf = bin_conf
        self.min_temp = min_temp
        self.max_temp = max_temp
        self.memory_efficient = memory_efficient
        self.train_midas = train_midas
        self.is_midas_pretrained = is_midas_pretrained
        self.midas_lr_factor = midas_lr_factor
        self.encoder_lr_factor = encoder_lr_factor
        self.pos_enc_lr_factor = pos_enc_lr_factor
        self.inverse_midas = inverse_midas

        N_MIDAS_OUT = 32
        btlnck_features = self.core.output_channels[0]
        num_out_features = self.core.output_channels[1:]
        # self.scales = [16, 8, 4, 2]  # spatial scale factors

        self.conv2 = nn.Conv2d(
            btlnck_features, btlnck_features, kernel_size=1, stride=1, padding=0)

        # Transformer classifier on the bottleneck
        self.patch_transformer = PatchTransformerEncoder(
            btlnck_features, 1, 128, use_class_token=True)
        self.mlp_classifier = nn.Sequential(
            nn.Linear(128, 128),
            nn.ReLU(),
            nn.Linear(128, 2)
        )

        if bin_centers_type == "normed":
            SeedBinRegressorLayer = SeedBinRegressor
            Attractor = AttractorLayer
        elif bin_centers_type == "softplus":
            SeedBinRegressorLayer = SeedBinRegressorUnnormed
            Attractor = AttractorLayerUnnormed
        elif bin_centers_type == "hybrid1":
            SeedBinRegressorLayer = SeedBinRegressor
            Attractor = AttractorLayerUnnormed
        elif bin_centers_type == "hybrid2":
            SeedBinRegressorLayer = SeedBinRegressorUnnormed
            Attractor = AttractorLayer
        else:
            raise ValueError(
                "bin_centers_type should be one of 'normed', 'softplus', 'hybrid1', 'hybrid2'")
        self.bin_centers_type = bin_centers_type
        # We have bins for each bin conf.
        # Create a map (ModuleDict) of 'name' -> seed_bin_regressor
        self.seed_bin_regressors = nn.ModuleDict(
            {conf['name']: SeedBinRegressorLayer(btlnck_features, conf["n_bins"], mlp_dim=bin_embedding_dim//2, min_depth=conf["min_depth"], max_depth=conf["max_depth"])
             for conf in bin_conf}
        )

        self.seed_projector = Projector(
            btlnck_features, bin_embedding_dim, mlp_dim=bin_embedding_dim//2)
        self.projectors = nn.ModuleList([
            Projector(num_out, bin_embedding_dim, mlp_dim=bin_embedding_dim//2)
            for num_out in num_out_features
        ])

        # Create a map (ModuleDict) of 'name' -> attractors (ModuleList)
        self.attractors = nn.ModuleDict(
            {conf['name']: nn.ModuleList([
                Attractor(bin_embedding_dim, n_attractors[i],
                          mlp_dim=bin_embedding_dim, alpha=attractor_alpha,
                          gamma=attractor_gamma, kind=attractor_kind,
                          attractor_type=attractor_type, memory_efficient=memory_efficient,
                          min_depth=conf["min_depth"], max_depth=conf["max_depth"])
                for i in range(len(n_attractors))
            ])
                for conf in bin_conf}
        )

        last_in = N_MIDAS_OUT
        # conditional log binomial for each bin conf
        self.conditional_log_binomial = nn.ModuleDict(
            {conf['name']: ConditionalLogBinomial(last_in, bin_embedding_dim, conf['n_bins'], bottleneck_factor=4, min_temp=self.min_temp, max_temp=self.max_temp)
             for conf in bin_conf}
        )