# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/pp_doclayout_v3/modular_pp_doclayout_v3.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_pp_doclayout_v3.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 huggingface_hub.dataclasses import strict from ...backbone_utils import consolidate_backbone_kwargs_to_config from ...configuration_utils import PreTrainedConfig from ...utils import auto_docstring from ..auto import AutoConfig @auto_docstring(checkpoint="PaddlePaddle/PP-DocLayoutV3_safetensors") @strict class PPDocLayoutV3Config(PreTrainedConfig): r""" initializer_bias_prior_prob (`float`, *optional*): The prior probability used by the bias initializer to initialize biases for `enc_score_head` and `class_embed`. If `None`, `prior_prob` computed as `prior_prob = 1 / (num_labels + 1)` while initializing model weights. freeze_backbone_batch_norms (`bool`, *optional*, defaults to `True`): Whether to freeze the batch normalization layers in the backbone. encoder_in_channels (`list`, *optional*, defaults to `[512, 1024, 2048]`): Multi level features input for encoder. feat_strides (`list[int]`, *optional*, defaults to `[8, 16, 32]`): Strides used in each feature map. encode_proj_layers (`list[int]`, *optional*, defaults to `[2]`): Indexes of the projected layers to be used in the encoder. positional_encoding_temperature (`int`, *optional*, defaults to 10000): The temperature parameter used to create the positional encodings. encoder_activation_function (`str`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. eval_size (`tuple[int, int]`, *optional*): Height and width used to computes the effective height and width of the position embeddings after taking into account the stride. normalize_before (`bool`, *optional*, defaults to `False`): Determine whether to apply layer normalization in the transformer encoder layer before self-attention and feed-forward modules. hidden_expansion (`float`, *optional*, defaults to 1.0): Expansion ratio to enlarge the dimension size of RepVGGBlock and CSPRepLayer. mask_feature_channels (`list[int]`, *optional*, defaults to `[64, 64]`): The channels of the multi-level features for mask enhancement. x4_feat_dim (`int`, *optional*, defaults to 128): The dimension of the x4 feature map. d_model (`int`, *optional*, defaults to 256): Dimension of the layers exclude hybrid encoder. num_prototypes (`int`, *optional*, defaults to 32): Dimension of the layers exclude mask query head. label_noise_ratio (`float`, *optional*, defaults to 0.4): The fraction of denoising labels to which random noise should be added. box_noise_scale (`float`, *optional*, defaults to 0.4): Scale or magnitude of noise to be added to the bounding boxes. mask_enhanced (`bool`, *optional*, defaults to `True`): Whether to use enhanced masked attention. num_queries (`int`, *optional*, defaults to 300): Number of object queries. decoder_in_channels (`list`, *optional*, defaults to `[256, 256, 256]`): Multi level features dimension for decoder decoder_ffn_dim (`int`, *optional*, defaults to 1024): Dimension of the "intermediate" (often named feed-forward) layer in decoder. num_feature_levels (`int`, *optional*, defaults to 3): The number of input feature levels. decoder_n_points (`int`, *optional*, defaults to 4): The number of sampled keys in each feature level for each attention head in the decoder. decoder_activation_function (`str`, *optional*, defaults to `"relu"`): The non-linear activation function (function or string) in the decoder. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. num_denoising (`int`, *optional*, defaults to 100): The total number of denoising tasks or queries to be used for contrastive denoising. learn_initial_query (`bool`, *optional*, defaults to `False`): Indicates whether the initial query embeddings for the decoder should be learned during training anchor_image_size (`tuple[int, int]`, *optional*): Height and width of the input image used during evaluation to generate the bounding box anchors. If None, automatic generate anchor is applied. disable_custom_kernels (`bool`, *optional*, defaults to `True`): Whether to disable custom kernels. global_pointer_head_size (`int`, *optional*, defaults to 64): The size of the global pointer head. gp_dropout_value (`float`, *optional*, defaults to 0.1): The dropout probability in the global pointer head. Examples: ```python >>> from transformers import PPDocLayoutV3Config, PPDocLayoutV3ForObjectDetection >>> # Initializing a PP-DocLayoutV3 configuration >>> configuration = PPDocLayoutV3Config() >>> # Initializing a model (with random weights) from the configuration >>> model = PPDocLayoutV3ForObjectDetection(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "pp_doclayout_v3" sub_configs = {"backbone_config": AutoConfig} layer_types = ("basic", "bottleneck") attribute_map = { "hidden_size": "d_model", "num_attention_heads": "encoder_attention_heads", } initializer_range: float = 0.01 initializer_bias_prior_prob: float | None = None layer_norm_eps: float = 1e-5 batch_norm_eps: float = 1e-5 tie_word_embeddings: bool = True backbone_config: dict | PreTrainedConfig | None = None freeze_backbone_batch_norms: bool = True encoder_hidden_dim: int = 256 encoder_in_channels: list[int] | tuple[int, ...] = (512, 1024, 2048) feat_strides: list[int] | tuple[int, ...] = (8, 16, 32) encoder_layers: int = 1 encoder_ffn_dim: int = 1024 encoder_attention_heads: int = 8 dropout: float | int = 0.0 activation_dropout: float | int = 0.0 encode_proj_layers: list[int] | tuple[int, ...] = (2,) positional_encoding_temperature: int = 10000 encoder_activation_function: str = "gelu" activation_function: str = "silu" eval_size: int | None = None normalize_before: bool = False hidden_expansion: float = 1.0 mask_feature_channels: list[int] | tuple[int, ...] = (64, 64) x4_feat_dim: int = 128 d_model: int = 256 num_prototypes: int = 32 label_noise_ratio: float = 0.4 box_noise_scale: float = 0.4 mask_enhanced: bool = True num_queries: int = 300 decoder_in_channels: list[int] | tuple[int, ...] = (256, 256, 256) decoder_ffn_dim: int = 1024 num_feature_levels: int = 3 decoder_n_points: int = 4 decoder_layers: int = 6 decoder_attention_heads: int = 8 decoder_activation_function: str = "relu" attention_dropout: float | int = 0.0 num_denoising: int = 100 learn_initial_query: bool = False anchor_image_size: int | None = None disable_custom_kernels: bool = True is_encoder_decoder: bool = True global_pointer_head_size: int = 64 gp_dropout_value: float | int = 0.1 def __post_init__(self, **kwargs): self.backbone_config, kwargs = consolidate_backbone_kwargs_to_config( backbone_config=self.backbone_config, default_config_type="hgnet_v2", default_config_kwargs={ "arch": "L", "return_idx": [0, 1, 2, 3], "freeze_stem_only": True, "freeze_at": 0, "freeze_norm": True, "lr_mult_list": [0, 0.05, 0.05, 0.05, 0.05], "out_features": ["stage1", "stage2", "stage3", "stage4"], }, **kwargs, ) self.encoder_in_channels = list(self.encoder_in_channels) self.feat_strides = list(self.feat_strides) self.encode_proj_layers = list(self.encode_proj_layers) self.eval_size = list(self.eval_size) if self.eval_size is not None else None self.decoder_in_channels = list(self.decoder_in_channels) self.anchor_image_size = list(self.anchor_image_size) if self.anchor_image_size is not None else None super().__post_init__(**kwargs) __all__ = ["PPDocLayoutV3Config"]