U ,-e?@sdZddlmZddlmZddlmZddlmZddl m Z ddl m Z dd l mZmZe eZd d iZGd d d eeZGddde ZdS)z% Swin Transformer model configuration OrderedDict)Mapping)version)PretrainedConfig) OnnxConfig)logging)BackboneConfigMixin*get_aligned_output_features_output_indiceszµsoft/swin-tiny-patch4-window7-224zVhttps://huggingface.co/microsoft/swin-tiny-patch4-window7-224/resolve/main/config.jsoncsfeZdZdZdZdddZdddd d d d d gdd d d gdddddddddddddffdd ZZS) SwinConfigaI This is the configuration class to store the configuration of a [`SwinModel`]. It is used to instantiate a Swin 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 Swin [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 4): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. embed_dim (`int`, *optional*, defaults to 96): Dimensionality of patch embedding. depths (`list(int)`, *optional*, defaults to [2, 2, 6, 2]): Depth of each layer in the Transformer encoder. num_heads (`list(int)`, *optional*, defaults to [3, 6, 12, 24]): Number of attention heads in each layer of the Transformer encoder. window_size (`int`, *optional*, defaults to 7): Size of windows. mlp_ratio (`float`, *optional*, defaults to 4.0): Ratio of MLP hidden dimensionality to embedding dimensionality. qkv_bias (`bool`, *optional*, defaults to True): Whether or not a learnable bias should be added to the queries, keys and values. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings and encoder. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. drop_path_rate (`float`, *optional*, defaults to 0.1): Stochastic depth rate. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. use_absolute_embeddings (`bool`, *optional*, defaults to False): Whether or not to add absolute position embeddings to the patch embeddings. 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. encoder_stride (`int`, `optional`, defaults to 32): Factor to increase the spatial resolution by in the decoder head for masked image modeling. 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. 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. Example: ```python >>> from transformers import SwinConfig, SwinModel >>> # Initializing a Swin microsoft/swin-tiny-patch4-window7-224 style configuration >>> configuration = SwinConfig() >>> # Initializing a model (with random weights) from the microsoft/swin-tiny-patch4-window7-224 style configuration >>> model = SwinModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zswin num_heads num_layers)Znum_attention_headsZnum_hidden_layersr` g@Tgg?ZgeluFg{Gz?gh㈵> Nc stjf|||_||_||_||_||_t||_||_ ||_ ||_ | |_ | |_ | |_| |_| |_||_||_||_||_t|dt|d|_dgddtdt|dD|_t|||jd\|_|_dS)NrstemcSsg|]}d|qS)Zstage).0idxrrl/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/swin/configuration_swin.py sz'SwinConfig.__init__..) out_features out_indices stage_names)super__init__ image_size patch_size num_channels embed_dimdepthslenrr window_size mlp_ratioqkv_biashidden_dropout_probattention_probs_dropout_probdrop_path_rate hidden_actuse_absolute_embeddingslayer_norm_epsinitializer_rangeencoder_strideintZ hidden_sizeranger!r Z _out_featuresZ _out_indices)selfr$r%r&r'r(r r*r+r,r-r.r/r0r1r3r2r4rr kwargs __class__rrr#ss4 $zSwinConfig.__init__)__name__ __module__ __qualname____doc__Z model_typeZ attribute_mapr# __classcell__rrr9rr &s2E  r c@sJeZdZedZeeeee effdddZ ee dddZ dS)SwinOnnxConfigz1.11)returncCstddddddfgS)NZ pixel_valuesbatchr&heightwidth)rrrrrr7rrrinputsszSwinOnnxConfig.inputscCsdS)Ng-C6?rrErrratol_for_validationsz"SwinOnnxConfig.atol_for_validationN) r;r<r=rparseZtorch_onnx_minimum_versionpropertyrstrr5rFfloatrGrrrrr@s   r@N)r> collectionsrtypingr packagingrZconfiguration_utilsrZonnxrutilsr Zutils.backbone_utilsr r Z get_loggerr;loggerZ"SWIN_PRETRAINED_CONFIG_ARCHIVE_MAPr r@rrrrs