Ë ©sg^ãól—dZddlmZddlmZddlmZmZeje «Z Gd„dee«Z y)z&Swinv2 Transformer model configurationé)ÚPretrainedConfig)Úlogging)ÚBackboneConfigMixinÚ*get_aligned_output_features_output_indicescóf‡—eZdZdZdZdddœZdddd gd ¢gd ¢d gd ¢ddddddddddddfˆfd„ ZˆxZS)Ú Swinv2Configa  This is the configuration class to store the configuration of a [`Swinv2Model`]. It is used to instantiate a Swin Transformer v2 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 Transformer v2 [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) 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. pretrained_window_sizes (`list(int)`, *optional*, defaults to `[0, 0, 0, 0]`): Size of windows during pretraining. 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-05): 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 Swinv2Config, Swinv2Model >>> # Initializing a Swinv2 microsoft/swinv2-tiny-patch4-window8-256 style configuration >>> configuration = Swinv2Config() >>> # Initializing a model (with random weights) from the microsoft/swinv2-tiny-patch4-window8-256 style configuration >>> model = Swinv2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Úswinv2Ú num_headsÚ num_layers)Únum_attention_headsÚnum_hidden_layerséàéré`)érér)rré éé)érrrg@Tggš™™™™™¹?ÚgeluFg{®Gáz”?gñh㈵øä>é Nc ó<•—t‰|di|¤Ž||_||_||_||_||_t|«|_||_ ||_ ||_ | |_ | |_ | |_| |_| |_||_||_||_||_||_dgt-dt|«dz«Dcgc]}d|›‘Œ c}z|_t1|||j.¬«\|_|_t7|dt|«dz zz«|_ycc}w)NÚsteméÚstage)Ú out_featuresÚ out_indicesÚ stage_namesr©)ÚsuperÚ__init__Ú image_sizeÚ patch_sizeÚ num_channelsÚ embed_dimÚdepthsÚlenr r Ú window_sizeÚpretrained_window_sizesÚ mlp_ratioÚqkv_biasÚhidden_dropout_probÚattention_probs_dropout_probÚdrop_path_rateÚ hidden_actÚuse_absolute_embeddingsÚlayer_norm_epsÚinitializer_rangeÚencoder_strideÚrangerrÚ _out_featuresÚ _out_indicesÚintÚ hidden_size)Úselfr#r$r%r&r'r r)r*r+r,r-r.r/r0r1r3r2r4rrÚkwargsÚidxÚ __class__s €úb/var/www/html/venv/lib/python3.12/site-packages/transformers/models/swinv2/configuration_swinv2.pyr"zSwinv2Config.__init__is!ø€ô0 ‰ÑÑ"˜6Ò"à$ˆŒØ$ˆŒØ(ˆÔØ"ˆŒØˆŒ ܘf›+ˆŒØ"ˆŒØ&ˆÔØ'>ˆÔ$Ø"ˆŒØ ˆŒ Ø#6ˆÔ Ø,HˆÔ)Ø,ˆÔØ$ˆŒØ'>ˆÔ$Ø,ˆÔØ!2ˆÔØ,ˆÔØ"˜8ÄÀaÌÈVËÐWXÉÓ@YÖ&Z¸¨¨s¨e¢}Ò&ZÑZˆÔÜ0ZØ%°;ÈD×L\ÑL\ô1 Ñ-ˆÔ˜DÔ-ô ˜y¨1´°V³¸q±Ñ+AÑAÓBˆÕùò '[sÂ; D)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚ attribute_mapr"Ú __classcell__)r=s@r>rrsjø„ñF ðP€Jð +Ø)ñ€MðØØØÚÚ ØÚ ,ØØØØ%(ØØØ %ØØØØØ÷+3Cñ3CórN) rBÚconfiguration_utilsrÚutilsrÚutils.backbone_utilsrrÚ get_loggerr?Úloggerrr rFr>úrLs;ðñ-å3Ýßcð ˆ× Ñ ˜HÓ %€ôCCÐ&Ð(8õCCrF