# coding=utf-8 # Copyright 2022 rinna Co., Ltd. # # 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. """ CLIP model configuration""" import logging import copy import os from typing import Union import numpy as np from transformers import AutoConfig, PretrainedConfig logger = logging.getLogger(__name__) class CLIPTextConfig(PretrainedConfig): model_type = "clip_text_model" def __init__( self, vocab_size=49408, hidden_size=512, intermediate_size=2048, num_hidden_layers=12, num_attention_heads=8, max_position_embeddings=77, hidden_act="quick_gelu", layer_norm_eps=0.00001, dropout=0.0, attention_dropout=0.0, initializer_range=0.02, initializer_factor=1.0, pad_token_id=1, bos_token_id=0, eos_token_id=2, **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.dropout = dropout self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads self.max_position_embeddings = max_position_embeddings self.layer_norm_eps = layer_norm_eps self.hidden_act = hidden_act self.initializer_range = initializer_range self.initializer_factor = initializer_factor self.attention_dropout = attention_dropout @classmethod def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig": config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) # get the text config dict if we are loading from CLIPConfig if config_dict.get("model_type") == "clip": config_dict = config_dict["text_config"] if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type: logger.warning( f"You are using a model of type {config_dict['model_type']} to instantiate a model of type " f"{cls.model_type}. This is not supported for all configurations of models and can yield errors." ) return cls.from_dict(config_dict, **kwargs) class CLIPVisionConfig(PretrainedConfig): model_type = "clip_vision_model" def __init__( self, hidden_size=768, intermediate_size=3072, num_hidden_layers=12, num_attention_heads=12, image_size=224, patch_size=32, hidden_act="quick_gelu", layer_norm_eps=0.00001, dropout=0.0, 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.dropout = dropout self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads self.patch_size = patch_size self.image_size = image_size self.initializer_range = initializer_range self.initializer_factor = initializer_factor self.attention_dropout = attention_dropout self.layer_norm_eps = layer_norm_eps self.hidden_act = hidden_act @classmethod def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig": config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) # get the vision config dict if we are loading from CLIPConfig if config_dict.get("model_type") == "clip": config_dict = config_dict["vision_config"] if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type: logger.warning( f"You are using a model of type {config_dict['model_type']} to instantiate a model of type " f"{cls.model_type}. This is not supported for all configurations of models and can yield errors." ) return cls.from_dict(config_dict, **kwargs) class CLIPConfig(PretrainedConfig): r""" [`CLIPConfig`] is the configuration class to store the configuration of a [`CLIPModel`]. It is used to instantiate CLIP model according to the specified arguments, defining the text model and vision model configs. 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 (`dict`, *optional*): Dictionary of configuration options used to initialize [`CLIPTextConfig`]. vision_config_dict (`dict`, *optional*): Dictionary of configuration options used to initialize [`CLIPVisionConfig`]. projection_dim (`int`, *optional*, defaults to 512): Dimentionality of text and vision projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The inital value of the *logit_scale* paramter. Default is used as per the original CLIP implementation. kwargs (*optional*): Dictionary of keyword arguments. """ model_type = "clip" is_composition = True def __init__( self, text_config=None, vision_config=None, projection_dim=512, logit_scale_init_value=None, **kwargs ): super().__init__(text_config=text_config, vision_config=vision_config, **kwargs) if vision_config is None: raise ValueError("`vision_config` can not be `None`.") if text_config is None: raise ValueError("`text_config` can not be `None`.") vision_model_type = vision_config.pop("model_type") text_model_type = text_config.pop("model_type") if vision_model_type == "clip_vision_model": self.vision_config = CLIPVisionConfig(**vision_config) else: self.vision_config = AutoConfig.for_model( vision_model_type, **vision_config ) if text_model_type == "clip_text_model": self.text_config = CLIPTextConfig(**text_config) else: self.text_config = AutoConfig.for_model( text_model_type, **text_config ) self.projection_dim = projection_dim self.logit_scale_init_value = logit_scale_init_value if logit_scale_init_value is not None else np.log(1 / 0.07) self.initializer_factor = 1.0 @classmethod def from_text_vision_configs(cls, text_config: CLIPTextConfig, vision_config: CLIPVisionConfig, **kwargs): r""" Instantiate a [`CLIPConfig`] (or a derived class) from clip text model configuration and clip vision model configuration. Returns: [`CLIPConfig`]: An instance of a configuration object """ return cls(text_config_dict=text_config.to_dict(), vision_config_dict=vision_config.to_dict(), **kwargs) def to_dict(self): """ Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`]. Returns: `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance, """ output = copy.deepcopy(self.__dict__) output["text_config"] = self.text_config.to_dict() output["vision_config"] = self.vision_config.to_dict() output["model_type"] = self.__class__.model_type return output