o h1@sbdZddlZddlmZddlmZddlmZddlm Z e e Z d d iZ Gd d d eZdS) z DPT model configurationN)PretrainedConfig)logging)CONFIG_MAPPING) BitConfigzIntel/dpt-largez?https://huggingface.co/Intel/dpt-large/resolve/main/config.jsoncs~eZdZdZdZddddddddd d d d d dgddgdgdddd dd ddddgdddgdffdd ZddZZS) 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 probabilitiy 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[str, Any], PretrainedConfig]`, *optional*): The configuration of the backbone model. Only used in case `is_hybrid` is `True` or in case you want to leverage the [`AutoBackbone`] API. 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 ```dpt i gelugg{Gz?g-q=rFT)r project)rg?)`r r Ng?g?)rirrrc# s&tjdi|||_| |_d} |jrf|dur2tdddgdgddd}tdi||_n%t|t rEtdtdi||_nt|t rN||_n t d |j d ||_ ||_|d kret d n,|durd} t|t r|d }!t|!}"|"|}||_d|_ g|_n ||_d|_ g|_| rdn||_| rdn||_| rdn||_| rdn||_| rdn||_| rdn| |_| rdn| |_| rdn| |_| rdn| |_| rdn||_| rdn||_|dvrt d||_||_||_||_ ||_!||_"||_#||_$||_%||_&||_'||_(||_)||_*dS)NFz.Initializing the config with a `BiT` backbone.same bottleneck)rr )stage1stage2stage3T)global_padding layer_typedepths out_featuresembedding_dynamic_paddingzBbackbone_config must be a dictionary or a `PretrainedConfig`, got .rzrFr?r@rArBr.rCrDrGrHrIrJrKrLrMrNrOrPrQrRr6r7r1kwargsuse_autobackbonebackbone_model_type config_classr5r*_/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/dpt/configuration_dpt.pyr,s"         zDPTConfig.__init__cCs6t|j}|ddur|j|d<|jj|d<|S)z Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`]. Returns: `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance, r1Nr')copydeepcopy__dict__r1to_dictr5r')rSoutputr*r*rYr]s   zDPTConfig.to_dict)__name__ __module__ __qualname____doc__r'r,r] __classcell__r*r*rXrYr!sF`sr)rbrZconfiguration_utilsrutilsrauto.configuration_autorbitr get_loggerr_r/!DPT_PRETRAINED_CONFIG_ARCHIVE_MAPrr*r*r*rYs