image-match/python/py/Lib/site-packages/transformers/models/uvdoc/configuration_uvdoc.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/uvdoc/modular_uvdoc.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_uvdoc.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2026 The PaddlePaddle Team and 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.


from collections.abc import Sequence

from huggingface_hub.dataclasses import strict

from ...backbone_utils import BackboneConfigMixin, consolidate_backbone_kwargs_to_config
from ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring
from ..auto import AutoConfig


@auto_docstring(checkpoint="PaddlePaddle/UVDoc_safetensors")
@strict
class UVDocBackboneConfig(BackboneConfigMixin, PreTrainedConfig):
    r"""
    resnet_head (`Sequence[list[int] | tuple[int, ...]]`, *optional*, defaults to `((3, 32), (32, 32))`):
        Configuration for the ResNet head layers in format [in_channels, out_channels].
    resnet_configs (`Sequence[Sequence[tuple[int, int, int, bool] | list[int | bool]]]`, *optional*, defaults to `(((32, 32, 1, False),
        (32, 32, 3, False), (32, 32, 3, False)), ((32, 64, 1, True), (64, 64, 3, False), (64, 64, 3, False), (64, 64, 3, False)), ((64, 128, 1, True),
        (128, 128, 3, False), (128, 128, 3, False), (128, 128, 3, False), (128, 128, 3, False), (128, 128, 3, False)))`):
        Configuration for the ResNet stages in format [in_channels, out_channels, dilation_value, downsample].
    stage_configs (Sequence[Sequence[tuple[int, ...] | list[int]]], *optional*, defaults to `(((128, 1),), ((128, 2),),
        ((128, 5),), ((128, 8),(128, 3),(128, 2),), ((128, 12), (128, 7), (128, 4),), ((128, 18), (128, 12), (128, 6),),)`):
        Configuration for the bridge module stages in format [in_channels, dilation_value].
        Each inner sequence corresponds to a single bridge block, and the outer sequence groups blocks by bridge stage.
    """

    model_type = "uvdoc_backbone"

    _out_features: list[str] | None = None
    _out_indices: list[int] | None = None

    resnet_head: Sequence[list[int] | tuple[int, ...]] = (
        (3, 32),
        (32, 32),
    )

    resnet_configs: Sequence[Sequence[tuple[int, int, int, bool] | list[int | bool]]] = (
        (
            (32, 32, 1, False),
            (32, 32, 3, False),
            (32, 32, 3, False),
        ),
        (
            (32, 64, 1, True),
            (64, 64, 3, False),
            (64, 64, 3, False),
            (64, 64, 3, False),
        ),
        (
            (64, 128, 1, True),
            (128, 128, 3, False),
            (128, 128, 3, False),
            (128, 128, 3, False),
            (128, 128, 3, False),
            (128, 128, 3, False),
        ),
    )

    stage_configs: Sequence[Sequence[tuple[int, ...] | list[int]]] = (
        ((128, 1),),
        ((128, 2),),
        ((128, 5),),
        (
            (128, 8),
            (128, 3),
            (128, 2),
        ),
        (
            (128, 12),
            (128, 7),
            (128, 4),
        ),
        (
            (128, 18),
            (128, 12),
            (128, 6),
        ),
    )

    kernel_size: int = 5

    def __post_init__(self, **kwargs):
        self.depths = [len(stages) for stages in self.stage_configs]
        self.stage_names = ["stem"] + [f"stage{idx}" for idx in range(1, len(self.stage_configs) + 1)]
        self.set_output_features_output_indices(
            out_indices=kwargs.pop("out_indices", None), out_features=kwargs.pop("out_features", None)
        )
        super().__post_init__(**kwargs)


@auto_docstring(checkpoint="PaddlePaddle/UVDoc_safetensors")
@strict
class UVDocConfig(PreTrainedConfig):
    r"""
    padding_mode (`str`, *optional*, defaults to `"reflect"`):
        Padding mode for convolutional layers. Supported modes are `"reflect"`, `"constant"`, and `"replicate"`.
    kernel_size (`int`, *optional*, defaults to 5):
        Kernel size for convolutional layers in the backbone network.
    bridge_connector (`list[int] | tuple[int, ...]`, *optional*, defaults to `(128, 128)`):
        Configuration for the bridge connector in format [in_channels, out_channels].
    out_point_positions2D (`Sequence[list[int] | tuple[int, ...]]`, *optional*, defaults to `((128, 32), (32, 2))`):
        Configuration for the output point positions 2D layer in format [in_channels, out_channels].
    """

    model_type = "uvdoc"
    sub_configs = {"backbone_config": AutoConfig}
    backbone_config: dict | PreTrainedConfig | None = None

    hidden_act: str = "prelu"
    padding_mode: str = "reflect"
    kernel_size: int = 5
    bridge_connector: list[int] | tuple[int, ...] = (128, 128)
    out_point_positions2D: Sequence[list[int] | tuple[int, ...]] = ((128, 32), (32, 2))

    def __post_init__(self, **kwargs):
        self.backbone_config, kwargs = consolidate_backbone_kwargs_to_config(
            backbone_config=self.backbone_config,
            default_config_type="uvdoc_backbone",
            **kwargs,
        )
        super().__post_init__(**kwargs)


__all__ = ["UVDocBackboneConfig", "UVDocConfig"]