# coding=utf-8 # Copyright 2023 The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """OWLv2 model configuration""" from typing import TYPE_CHECKING, Dict if TYPE_CHECKING: pass from ...configuration_utils import PretrainedConfig from ...utils import logging logger = logging.get_logger(__name__) # Copied from transformers.models.owlvit.configuration_owlvit.OwlViTTextConfig with OwlViT->Owlv2, owlvit-base-patch32->owlv2-base-patch16, owlvit->owlv2, OWL-ViT->OWLv2 class Owlv2TextConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of an [`Owlv2TextModel`]. It is used to instantiate an Owlv2 text encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Owlv2 [google/owlv2-base-patch16](https://huggingface.co/google/owlv2-base-patch16) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 49408): Vocabulary size of the OWLv2 text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Owlv2TextModel`]. hidden_size (`int`, *optional*, defaults to 512): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 2048): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. max_position_embeddings (`int`, *optional*, defaults to 16): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`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. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). pad_token_id (`int`, *optional*, defaults to 0): The id of the padding token in the input sequences. bos_token_id (`int`, *optional*, defaults to 49406): The id of the beginning-of-sequence token in the input sequences. eos_token_id (`int`, *optional*, defaults to 49407): The id of the end-of-sequence token in the input sequences. Example: ```python >>> from transformers import Owlv2TextConfig, Owlv2TextModel >>> # Initializing a Owlv2TextModel with google/owlv2-base-patch16 style configuration >>> configuration = Owlv2TextConfig() >>> # Initializing a Owlv2TextConfig from the google/owlv2-base-patch16 style configuration >>> model = Owlv2TextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "owlv2_text_model" base_config_key = "text_config" def __init__( self, vocab_size=49408, hidden_size=512, intermediate_size=2048, num_hidden_layers=12, num_attention_heads=8, max_position_embeddings=16, hidden_act="quick_gelu", layer_norm_eps=1e-5, attention_dropout=0.0, initializer_range=0.02, initializer_factor=1.0, pad_token_id=0, bos_token_id=49406, eos_token_id=49407, **kwargs, ): super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs) self.vocab_size = vocab_size self.hidden_size = hidden_size self.intermediate_size = intermediate_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads self.max_position_embeddings = max_position_embeddings self.hidden_act = hidden_act self.layer_norm_eps = layer_norm_eps self.attention_dropout = attention_dropout self.initializer_range = initializer_range self.initializer_factor = initializer_factor # Copied from transformers.models.owlvit.configuration_owlvit.OwlViTVisionConfig with OwlViT->Owlv2, owlvit-base-patch32->owlv2-base-patch16, owlvit->owlv2, OWL-ViT->OWLv2, 32->16 class Owlv2VisionConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of an [`Owlv2VisionModel`]. It is used to instantiate an OWLv2 image encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the OWLv2 [google/owlv2-base-patch16](https://huggingface.co/google/owlv2-base-patch16) 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. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. 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. num_channels (`int`, *optional*, defaults to 3): Number of channels in the input images. image_size (`int`, *optional*, defaults to 768): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`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. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). Example: ```python >>> from transformers import Owlv2VisionConfig, Owlv2VisionModel >>> # Initializing a Owlv2VisionModel with google/owlv2-base-patch16 style configuration >>> configuration = Owlv2VisionConfig() >>> # Initializing a Owlv2VisionModel model from the google/owlv2-base-patch16 style configuration >>> model = Owlv2VisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "owlv2_vision_model" base_config_key = "vision_config" def __init__( self, hidden_size=768, intermediate_size=3072, num_hidden_layers=12, num_attention_heads=12, num_channels=3, image_size=768, patch_size=16, hidden_act="quick_gelu", layer_norm_eps=1e-5, attention_dropout=0.0, initializer_range=0.02, initializer_factor=1.0, **kwargs, ): super().__init__(**kwargs) self.hidden_size = hidden_size self.intermediate_size = intermediate_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads self.num_channels = num_channels self.image_size = image_size self.patch_size = patch_size self.hidden_act = hidden_act self.layer_norm_eps = layer_norm_eps self.attention_dropout = attention_dropout self.initializer_range = initializer_range self.initializer_factor = initializer_factor # Copied from transformers.models.owlvit.configuration_owlvit.OwlViTConfig with OwlViT->Owlv2, owlvit-base-patch32->owlv2-base-patch16, owlvit->owlv2, OWL-ViT->OWLv2 class Owlv2Config(PretrainedConfig): r""" [`Owlv2Config`] is the configuration class to store the configuration of an [`Owlv2Model`]. It is used to instantiate an OWLv2 model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the OWLv2 [google/owlv2-base-patch16](https://huggingface.co/google/owlv2-base-patch16) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Owlv2TextConfig`]. vision_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`Owlv2VisionConfig`]. projection_dim (`int`, *optional*, defaults to 512): Dimensionality of text and vision projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The initial value of the *logit_scale* parameter. Default is used as per the original OWLv2 implementation. return_dict (`bool`, *optional*, defaults to `True`): Whether or not the model should return a dictionary. If `False`, returns a tuple. kwargs (*optional*): Dictionary of keyword arguments. """ model_type = "owlv2" sub_configs = {"text_config": Owlv2TextConfig, "vision_config": Owlv2VisionConfig} def __init__( self, text_config=None, vision_config=None, projection_dim=512, logit_scale_init_value=2.6592, return_dict=True, **kwargs, ): super().__init__(**kwargs) if text_config is None: text_config = {} logger.info("text_config is None. Initializing the Owlv2TextConfig with default values.") if vision_config is None: vision_config = {} logger.info("vision_config is None. initializing the Owlv2VisionConfig with default values.") self.text_config = Owlv2TextConfig(**text_config) self.vision_config = Owlv2VisionConfig(**vision_config) self.projection_dim = projection_dim self.logit_scale_init_value = logit_scale_init_value self.return_dict = return_dict self.initializer_factor = 1.0 @classmethod def from_text_vision_configs(cls, text_config: Dict, vision_config: Dict, **kwargs): r""" Instantiate a [`Owlv2Config`] (or a derived class) from owlv2 text model configuration and owlv2 vision model configuration. Returns: [`Owlv2Config`]: An instance of a configuration object """ config_dict = {} config_dict["text_config"] = text_config config_dict["vision_config"] = vision_config return cls.from_dict(config_dict, **kwargs) __all__ = ["Owlv2Config", "Owlv2TextConfig", "Owlv2VisionConfig"]