image-match/python/py/Lib/site-packages/transformers/models/eomt/configuration_eomt.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/eomt/modular_eomt.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_eomt.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 Mobile Perception Systems Lab at TU/e 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 huggingface_hub.dataclasses import strict

from ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring


@auto_docstring(checkpoint="tue-mps/coco_panoptic_eomt_large_640")
@strict
class EomtConfig(PreTrainedConfig):
    r"""
    layerscale_value (`float`, *optional*, defaults to 1.0):
        Initial value for the LayerScale parameter.
    num_upscale_blocks (`int`, *optional*, defaults to 2):
        Number of upsampling blocks used in the decoder or segmentation head.
    use_swiglu_ffn (`bool`, *optional*, defaults to `False`):
        Whether to use the SwiGLU feedforward neural network.
    num_blocks (`int`, *optional*, defaults to 4):
        Number of feature blocks or stages in the architecture.
    no_object_weight (`float`, *optional*, defaults to 0.1):
        Loss weight for the 'no object' class in panoptic/instance segmentation.
    class_weight (`float`, *optional*, defaults to 2.0):
        Loss weight for classification targets.
    mask_weight (`float`, *optional*, defaults to 5.0):
        Loss weight for mask prediction.
    train_num_points (`int`, *optional*, defaults to 12544):
        Number of points to sample for mask loss computation during training.
    oversample_ratio (`float`, *optional*, defaults to 3.0):
        Oversampling ratio used in point sampling for mask training.
    importance_sample_ratio (`float`, *optional*, defaults to 0.75):
        Ratio of points to sample based on importance during training.
    num_queries (`int`, *optional*, defaults to 200):
        Number of object queries in the Transformer.
    num_register_tokens (`int`, *optional*, defaults to 4):
        Number of learnable register tokens added to the transformer input.

    Example:

    ```python
    >>> from transformers import EomtConfig, EomtForUniversalSegmentation

    >>> # Initialize configuration
    >>> config = EomtConfig()

    >>> # Initialize model
    >>> model = EomtForUniversalSegmentation(config)

    >>> # Access config
    >>> config = model.config
    ```"""

    model_type = "eomt"

    hidden_size: int = 1024
    num_hidden_layers: int = 24
    num_attention_heads: int = 16
    hidden_act: str = "gelu"
    hidden_dropout_prob: float | int = 0.0
    initializer_range: float = 0.02
    layer_norm_eps: float = 1e-6
    image_size: int | list[int] | tuple[int, int] = 640
    patch_size: int | list[int] | tuple[int, int] = 16
    num_channels: int = 3
    mlp_ratio: int = 4
    layerscale_value: float = 1.0
    drop_path_rate: float | int = 0.0
    num_upscale_blocks: int = 2
    attention_dropout: float | int = 0.0
    use_swiglu_ffn: bool = False
    num_blocks: int = 4
    no_object_weight: float = 0.1
    class_weight: float = 2.0
    mask_weight: float = 5.0
    dice_weight: float = 5.0
    train_num_points: int = 12544
    oversample_ratio: float = 3.0
    importance_sample_ratio: float = 0.75
    num_queries: int = 200
    num_register_tokens: int = 4


__all__ = ["EomtConfig"]