qi-xdZddlmZddlmZddlmZddlmZeje Z GddeZ dgZ y ) zDPT model configuration)%consolidate_backbone_kwargs_to_config)PreTrainedConfig)logging) AutoConfigc eZdZdZdZdeiZdddddddd d d d d ddgddgdgddddddddddgdddgdddf fd ZxZS) DPTConfiga This is the configuration class to store the configuration of a [`DPTModel`]. It is used to instantiate an DPT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the DPT [Intel/dpt-large](https://huggingface.co/Intel/dpt-large) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. image_size (`int`, *optional*, defaults to 384): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. is_hybrid (`bool`, *optional*, defaults to `False`): Whether to use a hybrid backbone. Useful in the context of loading DPT-Hybrid models. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. backbone_out_indices (`list[int]`, *optional*, defaults to `[2, 5, 8, 11]`): Indices of the intermediate hidden states to use from backbone. readout_type (`str`, *optional*, defaults to `"project"`): The readout type to use when processing the readout token (CLS token) of the intermediate hidden states of the ViT backbone. Can be one of [`"ignore"`, `"add"`, `"project"`]. - "ignore" simply ignores the CLS token. - "add" passes the information from the CLS token to all other tokens by adding the representations. - "project" passes information to the other tokens by concatenating the readout to all other tokens before projecting the representation to the original feature dimension D using a linear layer followed by a GELU non-linearity. reassemble_factors (`list[int]`, *optional*, defaults to `[4, 2, 1, 0.5]`): The up/downsampling factors of the reassemble layers. neck_hidden_sizes (`list[str]`, *optional*, defaults to `[96, 192, 384, 768]`): The hidden sizes to project to for the feature maps of the backbone. fusion_hidden_size (`int`, *optional*, defaults to 256): The number of channels before fusion. head_in_index (`int`, *optional*, defaults to -1): The index of the features to use in the heads. use_batch_norm_in_fusion_residual (`bool`, *optional*, defaults to `False`): Whether to use batch normalization in the pre-activate residual units of the fusion blocks. use_bias_in_fusion_residual (`bool`, *optional*, defaults to `True`): Whether to use bias in the pre-activate residual units of the fusion blocks. add_projection (`bool`, *optional*, defaults to `False`): Whether to add a projection layer before the depth estimation head. use_auxiliary_head (`bool`, *optional*, defaults to `True`): Whether to use an auxiliary head during training. auxiliary_loss_weight (`float`, *optional*, defaults to 0.4): Weight of the cross-entropy loss of the auxiliary head. semantic_loss_ignore_index (`int`, *optional*, defaults to 255): The index that is ignored by the loss function of the semantic segmentation model. semantic_classifier_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the semantic classification head. backbone_featmap_shape (`list[int]`, *optional*, defaults to `[1, 1024, 24, 24]`): Used only for the `hybrid` embedding type. The shape of the feature maps of the backbone. neck_ignore_stages (`list[int]`, *optional*, defaults to `[0, 1]`): Used only for the `hybrid` embedding type. The stages of the readout layers to ignore. backbone_config (`Union[dict, "PreTrainedConfig"]`, *optional*, defaults to `BitConfig()`): The configuration of the backbone model. Only used in case `is_hybrid` is `True` or in case you want to leverage the [`AutoBackbone`] API. pooler_output_size (`int`, *optional*): Dimensionality of the pooler layer. If None, defaults to `hidden_size`. pooler_act (`str`, *optional*, defaults to `"tanh"`): The activation function to be used by the pooler. Example: ```python >>> from transformers import DPTModel, DPTConfig >>> # Initializing a DPT dpt-large style configuration >>> configuration = DPTConfig() >>> # Initializing a model from the dpt-large style configuration >>> model = DPTModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```dptbackbone_config i gelugg{Gz?g-q=rFT)r project)rg?)`rr Ng?g?)rirrtanhc! ||_| |_|dvr td|jrNt|tr|j ddt d|dddgdgdd d d |!\}}!|d k7r0td |!jd|t dd|i|!\}}!d}||_||_ ||_ ||_ ||_ ||_ | |_| |_| |_| |_||_||_| r|nd|_| r|ng|_||_||_||_||_||_||_||_||_||_||_||_ ||_!||_"||_#|r|n||_$| |_%tM"|di|!y)N)ignoreaddrz8Readout_type must be one of ['ignore', 'add', 'project'] model_typebitsame bottleneck)rr )stage1stage2stage3T)global_padding layer_typedepths out_featuresembedding_dynamic_padding)r default_config_typedefault_config_kwargsrzrHr?r@rArBr4rCrDrIrJrKrLrMrNrOrPrQrRrSrTrErFr rUrVkwargs __class__s# [/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/dpt/configuration_dpt.pyrXzDPTConfig.__init__sH'" ; ;WX X >>/40**<?&K ' /$)&,".'$B15 ' ' ' #OVy( !_`` ZZ # /?3N&K' /'' #OV$( ."3#6 !2#6 ,H),$$(  $8!@I&rksCC30   H %N# N#b -r]