o ZhZ @sdZddlmZddlmZddlmZddlmZddl m Z ddl m Z dd l mZmZe eZGd d d eeZGd d d e Zd d gZdS)zDINOv2 model configuration OrderedDict)Mapping)version)PretrainedConfig) OnnxConfig)logging)BackboneConfigMixin*get_aligned_output_features_output_indicescsPeZdZdZdZ              dfdd ZZS) Dinov2Configa This is the configuration class to store the configuration of a [`Dinov2Model`]. It is used to instantiate an Dinov2 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 Dinov2 [google/dinov2-base-patch16-224](https://huggingface.co/google/dinov2-base-patch16-224) 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. mlp_ratio (`int`, *optional*, defaults to 4): Ratio of the hidden size of the MLPs relative to the `hidden_size`. 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-06): The epsilon used by the layer normalization layers. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 14): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. layerscale_value (`float`, *optional*, defaults to 1.0): Initial value to use for layer scale. drop_path_rate (`float`, *optional*, defaults to 0.0): Stochastic depth rate per sample (when applied in the main path of residual layers). use_swiglu_ffn (`bool`, *optional*, defaults to `False`): Whether to use the SwiGLU feedforward neural network. out_features (`List[str]`, *optional*): If used as backbone, list of features to output. Can be any of `"stem"`, `"stage1"`, `"stage2"`, etc. (depending on how many stages the model has). If unset and `out_indices` is set, will default to the corresponding stages. If unset and `out_indices` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. out_indices (`List[int]`, *optional*): If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). If unset and `out_features` is set, will default to the corresponding stages. If unset and `out_features` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. apply_layernorm (`bool`, *optional*, defaults to `True`): Whether to apply layer normalization to the feature maps in case the model is used as backbone. reshape_hidden_states (`bool`, *optional*, defaults to `True`): Whether to reshape the feature maps to 4D tensors of shape `(batch_size, hidden_size, height, width)` in case the model is used as backbone. If `False`, the feature maps will be 3D tensors of shape `(batch_size, seq_len, hidden_size)`. use_mask_token (`bool`, *optional*, defaults to `True`): Whether to use mask_token in embeddings. Example: ```python >>> from transformers import Dinov2Config, Dinov2Model >>> # Initializing a Dinov2 dinov2-base-patch16-224 style configuration >>> configuration = Dinov2Config() >>> # Initializing a model (with random weights) from the dinov2-base-patch16-224 style configuration >>> model = Dinov2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zdinov2 gelu{Gz?ư>rT?FNc stjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_dgddtd|dD|_t|||jd\|_|_||_||_||_dS)NstemcSsg|]}d|qS)Zstage).0idxrr^/var/www/auris/lib/python3.10/site-packages/transformers/models/dinov2/configuration_dinov2.py sz)Dinov2Config.__init__..) out_features out_indices stage_namesr)super__init__ hidden_sizenum_hidden_layersnum_attention_heads mlp_ratio hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsqkv_biaslayerscale_valuedrop_path_rateuse_swiglu_ffnranger r Z _out_featuresZ _out_indicesapply_layernormreshape_hidden_statesuse_mask_token)selfr#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2rrr4r5r6kwargs __class__rrr"os0  zDinov2Config.__init__)r rrrrrrrrrrrTrrFNNTTT)__name__ __module__ __qualname____doc__Z model_typer" __classcell__rrr9rr s2Mr c@sJeZdZedZedeeee efffddZ ede fddZ dS)Dinov2OnnxConfigz1.11returncCstddddddfgS)NZ pixel_valuesbatchr.heightwidth)rrrrr7rrrinputsszDinov2OnnxConfig.inputscCsdS)Ng-C6?rrFrrratol_for_validationsz$Dinov2OnnxConfig.atol_for_validationN) r;r<r=rparseZtorch_onnx_minimum_versionpropertyrstrintrGfloatrHrrrrr@s   r@N)r> collectionsrtypingr packagingrZconfiguration_utilsrZonnxrutilsr Zutils.backbone_utilsr r Z get_loggerr;loggerr r@__all__rrrrs