o h@sdZddlmZddlmZmZmZddlmZddl m Z ddl m Z ddl mZeeZd d iZGd d d e ZGd dde ZdS)z Pvt model configuration OrderedDict)CallableListMapping)version)PretrainedConfig) OnnxConfig)loggingz pvt-tiny-224z,https://huggingface.co/Zetatech/pvt-tiny-224c%seZdZdZdZdddgdgdgdgd gd gd gd d d d dd dddfdedededeedeedeedeedeedeedeedeee fde de de d e d!e d"e d#ef$fd$d% Z Z S)& PvtConfigaM This is the configuration class to store the configuration of a [`PvtModel`]. It is used to instantiate an Pvt 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 Pvt [Xrenya/pvt-tiny-224](https://huggingface.co/Xrenya/pvt-tiny-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 input image size num_channels (`int`, *optional*, defaults to 3): The number of input channels. num_encoder_blocks (`int`, *optional*, defaults to 4): The number of encoder blocks (i.e. stages in the Mix Transformer encoder). depths (`List[int]`, *optional*, defaults to `[2, 2, 2, 2]`): The number of layers in each encoder block. sequence_reduction_ratios (`List[int]`, *optional*, defaults to `[8, 4, 2, 1]`): Sequence reduction ratios in each encoder block. hidden_sizes (`List[int]`, *optional*, defaults to `[64, 128, 320, 512]`): Dimension of each of the encoder blocks. patch_sizes (`List[int]`, *optional*, defaults to `[4, 2, 2, 2]`): Patch size before each encoder block. strides (`List[int]`, *optional*, defaults to `[4, 2, 2, 2]`): Stride before each encoder block. num_attention_heads (`List[int]`, *optional*, defaults to `[1, 2, 5, 8]`): Number of attention heads for each attention layer in each block of the Transformer encoder. mlp_ratios (`List[int]`, *optional*, defaults to `[8, 8, 4, 4]`): Ratio of the size of the hidden layer compared to the size of the input layer of the Mix FFNs in the encoder blocks. 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. drop_path_rate (`float`, *optional*, defaults to 0.0): The dropout probability for stochastic depth, used in the blocks of the Transformer encoder. layer_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. qkv_bias (`bool`, *optional*, defaults to `True`): Whether or not a learnable bias should be added to the queries, keys and values. num_labels ('int', *optional*, defaults to 1000): The number of classes. Example: ```python >>> from transformers import PvtModel, PvtConfig >>> # Initializing a PVT Xrenya/pvt-tiny-224 style configuration >>> configuration = PvtConfig() >>> # Initializing a model from the Xrenya/pvt-tiny-224 style configuration >>> model = PvtModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```pvtr)rrr)rr)@i@i)rrrr)rrr)rrrrgelugg{Gz?gư>Ti image_size num_channelsnum_encoder_blocksdepthssequence_reduction_ratios hidden_sizes patch_sizesstridesnum_attention_heads mlp_ratios hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangedrop_path_ratelayer_norm_epsqkv_bias num_labelsc stjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_||_||_||_||_dS)N)super__init__rrrrrrrrr rr!r"r#r$r%r&r(r')selfrrrrrrrrrr r!r"r#r$r%r&r'r(kwargs __class__r)_/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/pvt/configuration_pvt.pyr+gs& zPvtConfig.__init__)__name__ __module__ __qualname____doc__ model_typeintrrstrrfloatboolr+ __classcell__r)r)r.r0r %st?     r c@s\eZdZedZedeeee efffddZ ede fddZ ede fddZ d S) PvtOnnxConfigz1.11returncCstddddddfgS)N pixel_valuesbatchrheightwidth)rrrrrr,r)r)r0inputsszPvtOnnxConfig.inputscCdS)Ng-C6?r)rAr)r)r0atol_for_validationz!PvtOnnxConfig.atol_for_validationcCrC)N r)rAr)r)r0default_onnx_opsetrEz PvtOnnxConfig.default_onnx_opsetN)r1r2r3rparsetorch_onnx_minimum_versionpropertyrr7r6rBr8rDrGr)r)r)r0r;s  r;N)r4 collectionsrtypingrrr packagingrconfiguration_utilsr onnxr utilsr get_loggerr1logger!PVT_PRETRAINED_CONFIG_ARCHIVE_MAPr r;r)r)r)r0s      n