`i4ddlmZGddeZdgZdS))PretrainedConfigczeZdZdZdZ ddededededededeffd ZxZS) EomtConfiga This is the configuration class to store the configuration of a [`EomtForUniversalSegmentation`]. It is used to instantiate an EoMT 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 EoMT [tue-mps/coco_panoptic_eomt_large_640](https://huggingface.co/tue-mps/coco_panoptic_eomt_large_640) 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 1024): Dimensionality of the hidden representations. num_hidden_layers (`int`, *optional*, defaults to 24): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads in each attention layer. mlp_ratio (`int`, *optional*, defaults to 4): Ratio of the MLP hidden dimensionality to the hidden size. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings and encoder. 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 640): The size (resolution) of each input 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. layerscale_value (`float`, *optional*, defaults to 1.0): Initial value for the LayerScale parameter. drop_path_rate (`float`, *optional*, defaults to 0.0): The stochastic depth rate (drop path) used during training. num_upscale_blocks (`int`, *optional*, defaults to 2): Number of upsampling blocks used in the decoder or segmentation head. attention_dropout (`float`, *optional*, defaults to 0.0): Dropout probability applied after attention projection. use_swiglu_ffn (`bool`, *optional*, defaults to `False`): Whether to use the SwiGLU feedforward neural network. num_blocks (`int`, *optional*, defaults to 4): Number of feature blocks or stages in the architecture. no_object_weight (`float`, *optional*, defaults to 0.1): Loss weight for the 'no object' class in panoptic/instance segmentation. class_weight (`float`, *optional*, defaults to 2.0): Loss weight for classification targets. mask_weight (`float`, *optional*, defaults to 5.0): Loss weight for mask prediction. dice_weight (`float`, *optional*, defaults to 5.0): Loss weight for the dice loss component. train_num_points (`int`, *optional*, defaults to 12544): Number of points to sample for mask loss computation during training. oversample_ratio (`float`, *optional*, defaults to 3.0): Oversampling ratio used in point sampling for mask training. importance_sample_ratio (`float`, *optional*, defaults to 0.75): Ratio of points to sample based on importance during training. num_queries (`int`, *optional*, defaults to 200): Number of object queries in the Transformer. num_register_tokens (`int`, *optional*, defaults to 4): Number of learnable register tokens added to the transformer input. Example: ```python >>> from transformers import EomtConfig, EomtForUniversalSegmentation >>> # Initialize configuration >>> config = EomtConfig() >>> # Initialize model >>> model = EomtForUniversalSegmentation(config) >>> # Access config >>> config = model.config ```eomtgelu{Gz?ư>r?F皙?@@1@?no_object_weight class_weight mask_weight dice_weighttrain_num_pointsoversample_ratioimportance_sample_ratioc tjdi|||_||_||_||_||_||_||_| |_ | |_ | |_ ||_ ||_ | |_| |_||_||_||_||_||_||_||_||_||_||_||_||_dS)N)super__init__ hidden_sizenum_hidden_layersnum_attention_heads hidden_acthidden_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channels mlp_ratioattention_dropoutlayerscale_valuedrop_path_ratenum_upscale_blocksuse_swiglu_ffn num_blocksrrrrrrr num_queriesnum_register_tokens)selfr$r%r&r.r'r(r)r*r+r,r-r0r1r2r/r3r4rrrrrrrr5r6kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/eomt/configuration_eomt.pyr#zEomtConfig.__init__ks< ""6"""&!2#6 $#6 !2,$$("!2 0,"4,$ 0(&& 0 0'>$&#6   )rrr r r r r rrr rrr rr Fr rrrrrrrrr ) __name__ __module__ __qualname____doc__ model_typefloatintr# __classcell__)r9s@r:rrsM M ^J"%!  %"%)-7:7:7& ':7():7*+:7,-:7./:70 1:72"'3:7:7:7:7:7:7:7:7:7:7r;rN)configuration_utilsrr__all__r!r;r:rFsZ,433333L7L7L7L7L7!L7L7L7^ .r;