# Copyright 2022 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. """CLIPSeg model configuration""" from huggingface_hub.dataclasses import strict from ...configuration_utils import PreTrainedConfig from ...utils import auto_docstring, logging logger = logging.get_logger(__name__) @auto_docstring(checkpoint="CIDAS/clipseg-rd64") @strict class CLIPSegTextConfig(PreTrainedConfig): r""" Example: ```python >>> from transformers import CLIPSegTextConfig, CLIPSegTextModel >>> # Initializing a CLIPSegTextConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegTextConfig() >>> # Initializing a CLIPSegTextModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "clipseg_text_model" base_config_key = "text_config" vocab_size: int = 49408 hidden_size: int = 512 intermediate_size: int = 2048 num_hidden_layers: int = 12 num_attention_heads: int = 8 max_position_embeddings: int = 77 hidden_act: str = "quick_gelu" layer_norm_eps: float = 1e-5 attention_dropout: float | int = 0.0 initializer_range: float = 0.02 initializer_factor: float = 1.0 pad_token_id: int | None = 1 bos_token_id: int | None = 49406 eos_token_id: int | list[int] | None = 49407 @auto_docstring(checkpoint="CIDAS/clipseg-rd64") @strict class CLIPSegVisionConfig(PreTrainedConfig): r""" Example: ```python >>> from transformers import CLIPSegVisionConfig, CLIPSegVisionModel >>> # Initializing a CLIPSegVisionConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegVisionConfig() >>> # Initializing a CLIPSegVisionModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "clipseg_vision_model" base_config_key = "vision_config" hidden_size: int = 768 intermediate_size: int = 3072 num_hidden_layers: int = 12 num_attention_heads: int = 12 num_channels: int = 3 image_size: int | list[int] | tuple[int, int] = 224 patch_size: int | list[int] | tuple[int, int] = 32 hidden_act: str = "quick_gelu" layer_norm_eps: float = 1e-5 attention_dropout: float | int = 0.0 initializer_range: float = 0.02 initializer_factor: float = 1.0 @auto_docstring(checkpoint="CIDAS/clipseg-rd64") @strict class CLIPSegConfig(PreTrainedConfig): r""" extract_layers (`list[int]`, *optional*, defaults to `[3, 6, 9]`): Layers to extract when forwarding the query image through the frozen visual backbone of CLIP. reduce_dim (`int`, *optional*, defaults to 64): Dimensionality to reduce the CLIP vision embedding. conditional_layer (`int`, *optional*, defaults to 0): The layer to use of the Transformer encoder whose activations will be combined with the condition embeddings using FiLM (Feature-wise Linear Modulation). If 0, the last layer is used. use_complex_transposed_convolution (`bool`, *optional*, defaults to `False`): Whether to use a more complex transposed convolution in the decoder, enabling more fine-grained segmentation.. Example: ```python >>> from transformers import CLIPSegConfig, CLIPSegModel >>> # Initializing a CLIPSegConfig with CIDAS/clipseg-rd64 style configuration >>> configuration = CLIPSegConfig() >>> # Initializing a CLIPSegModel (with random weights) from the CIDAS/clipseg-rd64 style configuration >>> model = CLIPSegModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a CLIPSegConfig from a CLIPSegTextConfig and a CLIPSegVisionConfig >>> # Initializing a CLIPSegText and CLIPSegVision configuration >>> config_text = CLIPSegTextConfig() >>> config_vision = CLIPSegVisionConfig() >>> config = CLIPSegConfig(text_config=config_text, vision_config=config_vision) ```""" model_type = "clipseg" sub_configs = {"text_config": CLIPSegTextConfig, "vision_config": CLIPSegVisionConfig} text_config: dict | CLIPSegTextConfig | None = None vision_config: dict | CLIPSegVisionConfig | None = None projection_dim: int | None = 512 logit_scale_init_value: float | int | None = 2.6592 initializer_factor: float | None = 1.0 extract_layers: list[int] | tuple[int, ...] = (3, 6, 9) reduce_dim: int = 64 decoder_num_attention_heads: int = 4 decoder_attention_dropout: float | int = 0.0 decoder_hidden_act: str = "quick_gelu" decoder_intermediate_size: int = 2048 conditional_layer: int = 0 use_complex_transposed_convolution: bool = False def __post_init__(self, **kwargs): if self.text_config is None: text_config = {} logger.info("`text_config` is `None`. Initializing the `CLIPSegTextConfig` with default values.") elif isinstance(self.text_config, CLIPSegTextConfig): text_config = self.text_config.to_dict() else: text_config = self.text_config if self.vision_config is None: vision_config = {} logger.info("`vision_config` is `None`. initializing the `CLIPSegVisionConfig` with default values.") elif isinstance(self.vision_config, CLIPSegVisionConfig): vision_config = self.vision_config.to_dict() else: vision_config = self.vision_config # For backward compatibility check keyword args # Instead of simply assigning `[text|vision]_config_dict` to `[text|vision]_config`, we use the values in # `[text|vision]_config_dict` to update the values in `[text|vision]_config`. The values should be same in most # cases, but we don't want to break anything regarding `_config_dict` that existed before commit `8827e1b2`. text_config_dict = kwargs.pop("text_config_dict", None) vision_config_dict = kwargs.pop("vision_config_dict", None) if text_config_dict is not None: # This is the complete result when using `text_config_dict`. _text_config_dict = CLIPSegTextConfig(**text_config_dict).to_dict() # Give a warning if the values exist in both `_text_config_dict` and `text_config` but being different. for key, value in _text_config_dict.items(): if key in text_config and value != text_config[key] and key != "transformers_version": # If specified in `text_config_dict` if key in text_config_dict: message = ( f"`{key}` is found in both `text_config_dict` and `text_config` but with different values. " f'The value `text_config_dict["{key}"]` will be used instead.' ) # If inferred from default argument values (just to be super careful) else: message = ( f"`text_config_dict` is provided which will be used to initialize `CLIPSegTextConfig`. The " f'value `text_config["{key}"]` will be overridden.' ) logger.info(message) # Update all values in `text_config` with the ones in `_text_config_dict`. text_config.update(_text_config_dict) if vision_config_dict is not None: # This is the complete result when using `vision_config_dict`. _vision_config_dict = CLIPSegVisionConfig(**vision_config_dict).to_dict() # convert keys to string instead of integer if "id2label" in _vision_config_dict: _vision_config_dict["id2label"] = { str(key): value for key, value in _vision_config_dict["id2label"].items() } # Give a warning if the values exist in both `_vision_config_dict` and `vision_config` but being different. for key, value in _vision_config_dict.items(): if key in vision_config and value != vision_config[key] and key != "transformers_version": # If specified in `vision_config_dict` if key in vision_config_dict: message = ( f"`{key}` is found in both `vision_config_dict` and `vision_config` but with different " f'values. The value `vision_config_dict["{key}"]` will be used instead.' ) # If inferred from default argument values (just to be super careful) else: message = ( f"`vision_config_dict` is provided which will be used to initialize `CLIPSegVisionConfig`. " f'The value `vision_config["{key}"]` will be overridden.' ) logger.info(message) # Update all values in `vision_config` with the ones in `_vision_config_dict`. vision_config.update(_vision_config_dict) # Finally we can convert back our unified text/vision configs to `PretrainedConfig` self.text_config = CLIPSegTextConfig(**text_config) self.vision_config = CLIPSegVisionConfig(**vision_config) super().__post_init__(**kwargs) __all__ = ["CLIPSegConfig", "CLIPSegTextConfig", "CLIPSegVisionConfig"]