image-match/python/py/Lib/site-packages/transformers/models/edgetam/configuration_edgetam.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/edgetam/modular_edgetam.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_edgetam.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 The Meta AI Authors and 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


@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
@strict
class EdgeTamVisionConfig(PreTrainedConfig):
    r"""
    backbone_channel_list (`List[int]`, *optional*, defaults to `[384, 192, 96, 48]`):
        The list of channel dimensions for the backbone.
    backbone_feature_sizes (`List[List[int]]`, *optional*, defaults to `[[256, 256], [128, 128], [64, 64]]`):
        The spatial sizes of the feature maps from the backbone.
    fpn_hidden_size (`int`, *optional*, defaults to 256):
        The hidden dimension of the FPN.
    fpn_kernel_size (`int`, *optional*, defaults to 1):
        The kernel size for the convolutions in the neck.
    fpn_stride (`int`, *optional*, defaults to 1):
        The stride for the convolutions in the neck.
    fpn_padding (`int`, *optional*, defaults to 0):
        The padding for the convolutions in the neck.
    fpn_top_down_levels (`List[int]`, *optional*, defaults to `[2, 3]`):
        The levels for the top-down FPN connections.
    num_feature_levels (`int`, *optional*, defaults to 3):
        The number of feature levels from the FPN to use.
    """

    base_config_key = "vision_config"
    model_type = "edgetam_vision_model"
    sub_configs = {
        "backbone_config": AutoConfig,
    }

    backbone_config: dict | PreTrainedConfig | None = None
    backbone_channel_list: list[int] | None = None
    backbone_feature_sizes: list | None = None
    fpn_hidden_size: int = 256
    fpn_kernel_size: int = 1
    fpn_stride: int = 1
    fpn_padding: int = 0
    fpn_top_down_levels: list[int] | None = None
    num_feature_levels: int = 3
    hidden_act: str = "gelu"
    layer_norm_eps: float = 1e-6
    initializer_range: float = 0.02

    def __post_init__(self, **kwargs):
        self.backbone_channel_list = (
            [384, 192, 96, 48] if self.backbone_channel_list is None else self.backbone_channel_list
        )
        self.backbone_feature_sizes = (
            [[256, 256], [128, 128], [64, 64]] if self.backbone_feature_sizes is None else self.backbone_feature_sizes
        )
        self.fpn_top_down_levels = [2, 3] if self.fpn_top_down_levels is None else self.fpn_top_down_levels

        if isinstance(self.backbone_config, dict):
            self.backbone_config["model_type"] = self.backbone_config.get("model_type", "timm_wrapper")
            self.backbone_config = CONFIG_MAPPING[self.backbone_config["model_type"]](**self.backbone_config)
        elif self.backbone_config is None:
            self.backbone_config = AutoConfig.from_pretrained(
                "timm/repvit_m1.dist_in1k",
                model_args={"in_chans": 3, "features_only": True, "out_indices": [0, 1, 2, 3]},
            )
        super().__post_init__(**kwargs)


@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
@strict
class EdgeTamPromptEncoderConfig(PreTrainedConfig):
    r"""
    mask_input_channels (`int`, *optional*, defaults to 16):
        The number of channels to be fed to the `MaskDecoder` module.
    num_point_embeddings (`int`, *optional*, defaults to 4):
        The number of point embeddings to be used.
    scale (`float`, *optional*, defaults to 1):
        The scale factor for the prompt encoder.
    """

    base_config_key = "prompt_encoder_config"

    hidden_size: int = 256
    image_size: int | list[int] | tuple[int, int] = 1024
    patch_size: int | list[int] | tuple[int, int] = 16
    mask_input_channels: int = 16
    num_point_embeddings: int = 4
    hidden_act: str = "gelu"
    layer_norm_eps: float = 1e-6
    scale: int = 1


@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
@strict
class EdgeTamMaskDecoderConfig(PreTrainedConfig):
    r"""
    mlp_dim (`int`, *optional*, defaults to 2048):
        The dimension of the MLP in the two-way transformer.
    attention_downsample_rate (`int`, *optional*, defaults to 2):
        The downsample rate for the attention layers.
    num_multimask_outputs (`int`, *optional*, defaults to 3):
        The number of multimask outputs.
    iou_head_depth (`int`, *optional*, defaults to 3):
        The depth of the IoU head.
    iou_head_hidden_dim (`int`, *optional*, defaults to 256):
        The hidden dimension of the IoU head.
    dynamic_multimask_via_stability (`bool`, *optional*, defaults to `True`):
        Whether to use dynamic multimask via stability.
    dynamic_multimask_stability_delta (`float`, *optional*, defaults to 0.05):
        The stability delta for the dynamic multimask.
    dynamic_multimask_stability_thresh (`float`, *optional*, defaults to 0.98):
        The stability threshold for the dynamic multimask.
    """

    base_config_key = "mask_decoder_config"

    hidden_size: int = 256
    hidden_act: str = "gelu"
    mlp_dim: int = 2048
    num_hidden_layers: int = 2
    num_attention_heads: int = 8
    attention_downsample_rate: int = 2
    num_multimask_outputs: int = 3
    iou_head_depth: int = 3
    iou_head_hidden_dim: int = 256
    dynamic_multimask_via_stability: bool = True
    dynamic_multimask_stability_delta: float = 0.05
    dynamic_multimask_stability_thresh: float = 0.98


@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
@strict
class EdgeTamConfig(PreTrainedConfig):
    r"""
    prompt_encoder_config (Union[`dict`, `EdgeTamPromptEncoderConfig`], *optional*):
        Dictionary of configuration options used to initialize [`EdgeTamPromptEncoderConfig`].
    mask_decoder_config (Union[`dict`, `EdgeTamMaskDecoderConfig`], *optional*):
        Dictionary of configuration options used to initialize [`EdgeTamMaskDecoderConfig`].

     Example:

     ```python
     >>> from transformers import (
     ...     EdgeTamVisionConfig,
     ...     EdgeTamPromptEncoderConfig,
     ...     EdgeTamMaskDecoderConfig,
     ...     EdgeTamModel,
     ... )

     >>> # Initializing a EdgeTamConfig with `"facebook/edgetam.1_hiera_tiny"` style configuration
     >>> configuration = EdgeTamConfig()

     >>> # Initializing a EdgeTamModel (with random weights) from the `"facebook/edgetam.1_hiera_tiny"` style configuration
     >>> model = EdgeTamModel(configuration)

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

     >>> # We can also initialize a EdgeTamConfig from a EdgeTamVisionConfig, EdgeTamPromptEncoderConfig, and EdgeTamMaskDecoderConfig
     >>> # Initializing EDGETAM vision encoder, memory attention, and memory encoder configurations
     >>> vision_config = EdgeTamVisionConfig()
     >>> prompt_encoder_config = EdgeTamPromptEncoderConfig()
     >>> mask_decoder_config = EdgeTamMaskDecoderConfig()

     >>> config = EdgeTamConfig(vision_config, prompt_encoder_config, mask_decoder_config)
     ```
    """

    model_type = "edgetam"
    sub_configs = {
        "vision_config": AutoConfig,
        "prompt_encoder_config": EdgeTamPromptEncoderConfig,
        "mask_decoder_config": EdgeTamMaskDecoderConfig,
    }

    vision_config: dict | PreTrainedConfig | None = None
    prompt_encoder_config: dict | PreTrainedConfig | None = None
    mask_decoder_config: dict | PreTrainedConfig | None = None
    initializer_range: float = 0.02

    def __post_init__(self, **kwargs):
        if isinstance(self.vision_config, dict):
            self.vision_config["model_type"] = self.vision_config.get("model_type", "edgetam_vision_model")
            self.vision_config = CONFIG_MAPPING[self.vision_config["model_type"]](**self.vision_config)
        elif self.vision_config is None:
            self.vision_config = CONFIG_MAPPING["edgetam_vision_model"]()

        if isinstance(self.prompt_encoder_config, dict):
            self.prompt_encoder_config = EdgeTamPromptEncoderConfig(**self.prompt_encoder_config)
        elif self.prompt_encoder_config is None:
            self.prompt_encoder_config = EdgeTamPromptEncoderConfig()

        if isinstance(self.mask_decoder_config, dict):
            self.mask_decoder_config = EdgeTamMaskDecoderConfig(**self.mask_decoder_config)
        elif self.mask_decoder_config is None:
            self.mask_decoder_config = EdgeTamMaskDecoderConfig()

        super().__post_init__(**kwargs)


__all__ = ["EdgeTamConfig", "EdgeTamVisionConfig", "EdgeTamPromptEncoderConfig", "EdgeTamMaskDecoderConfig"]