image-match/python/py/Lib/site-packages/transformers/models/lightglue/configuration_lightglue.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/lightglue/modular_lightglue.py.
#               Do NOT edit this file manually as any edits will be overwritten by the generation of
#             the file from the modular. If any change should be done, please apply the change to the
#                          modular_lightglue.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 The HuggingFace 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.

from huggingface_hub.dataclasses import strict

from ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring
from ..auto import CONFIG_MAPPING, AutoConfig
from ..superpoint import SuperPointConfig


@auto_docstring(checkpoint="ETH-CVG/lightglue_superpoint")
@strict
class LightGlueConfig(PreTrainedConfig):
    r"""
    keypoint_detector_config (`Union[AutoConfig, dict]`,  *optional*, defaults to `SuperPointConfig`):
        The config object or dictionary of the keypoint detector.
    descriptor_dim (`int`, *optional*, defaults to 256):
        The dimension of the descriptors.
    depth_confidence (`float`, *optional*, defaults to 0.95):
        The confidence threshold used to perform early stopping
    width_confidence (`float`, *optional*, defaults to 0.99):
        The confidence threshold used to prune points
    filter_threshold (`float`, *optional*, defaults to 0.1):
        The confidence threshold used to filter matches

    Examples:
        ```python
        >>> from transformers import LightGlueConfig, LightGlueForKeypointMatching

        >>> # Initializing a LightGlue style configuration
        >>> configuration = LightGlueConfig()

        >>> # Initializing a model from the LightGlue style configuration
        >>> model = LightGlueForKeypointMatching(configuration)

        >>> # Accessing the model configuration
        >>> configuration = model.config
        ```
    """

    model_type = "lightglue"
    sub_configs = {"keypoint_detector_config": AutoConfig}

    keypoint_detector_config: dict | SuperPointConfig | None = None
    descriptor_dim: int = 256
    num_hidden_layers: int = 9
    num_attention_heads: int = 4
    num_key_value_heads: int | None = None
    depth_confidence: float = 0.95
    width_confidence: float = 0.99
    filter_threshold: float = 0.1
    initializer_range: float = 0.02
    hidden_act: str = "gelu"
    attention_dropout: float | int = 0.0
    attention_bias: bool = True

    def __post_init__(self, **kwargs):
        if self.num_key_value_heads is None:
            self.num_key_value_heads = self.num_attention_heads

        # Keypoint Detector is forced into eager attention mode because SuperPoint does not have Attention
        # See https://github.com/huggingface/transformers/pull/31718#discussion_r2109733153
        if isinstance(self.keypoint_detector_config, dict):
            self.keypoint_detector_config["model_type"] = self.keypoint_detector_config.get("model_type", "superpoint")
            self.keypoint_detector_config = CONFIG_MAPPING[self.keypoint_detector_config["model_type"]](
                **self.keypoint_detector_config, attn_implementation="eager"
            )
        elif self.keypoint_detector_config is None:
            self.keypoint_detector_config = CONFIG_MAPPING["superpoint"](attn_implementation="eager")

        self.intermediate_size = self.descriptor_dim * 2
        self.hidden_size = self.descriptor_dim
        super().__post_init__(**kwargs)

    def validate_architecture(self):
        """Part of `@strict`-powered validation. Validates the architecture of the config."""
        if self.descriptor_dim % self.num_attention_heads != 0:
            raise ValueError("descriptor_dim % num_heads is different from zero")


__all__ = ["LightGlueConfig"]