# coding=utf-8 # Copyright 2024 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. """VitPose backbone configuration""" from ...configuration_utils import PretrainedConfig from ...utils import logging from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_features_output_indices logger = logging.get_logger(__name__) class VitPoseBackboneConfig(BackboneConfigMixin, PretrainedConfig): r""" This is the configuration class to store the configuration of a [`VitPoseBackbone`]. It is used to instantiate a VitPose model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the VitPose [usyd-community/vitpose-base-simple](https://huggingface.co/usyd-community/vitpose-base-simple) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: image_size (`int`, *optional*, defaults to `[256, 192]`): The size (resolution) of each image. patch_size (`List[int]`, *optional*, defaults to `[16, 16]`): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. mlp_ratio (`int`, *optional*, defaults to 4): The ratio of the hidden size in the feedforward network to the hidden size in the attention layers. num_experts (`int`, *optional*, defaults to 1): The number of experts in the MoE layer. part_features (`int`, *optional*): The number of part features to output. Only used in case `num_experts` is greater than 1. hidden_act (`str`, *optional*, defaults to `"gelu"`): The non-linear activation function in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. out_features (`List[str]`, *optional*): If used as backbone, list of features to output. Can be any of `"stem"`, `"stage1"`, `"stage2"`, etc. (depending on how many stages the model has). If unset and `out_indices` is set, will default to the corresponding stages. If unset and `out_indices` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. out_indices (`List[int]`, *optional*): If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). If unset and `out_features` is set, will default to the corresponding stages. If unset and `out_features` is unset, will default to the last stage. Must be in the same order as defined in the `stage_names` attribute. Example: ```python >>> from transformers import VitPoseBackboneConfig, VitPoseBackbone >>> # Initializing a VitPose configuration >>> configuration = VitPoseBackboneConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = VitPoseBackbone(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "vitpose_backbone" def __init__( self, image_size=[256, 192], patch_size=[16, 16], num_channels=3, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, mlp_ratio=4, num_experts=1, part_features=256, hidden_act="gelu", hidden_dropout_prob=0.0, attention_probs_dropout_prob=0.0, initializer_range=0.02, layer_norm_eps=1e-12, qkv_bias=True, out_features=None, out_indices=None, **kwargs, ): super().__init__(**kwargs) self.hidden_size = hidden_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads self.mlp_ratio = mlp_ratio self.num_experts = num_experts self.part_features = part_features self.hidden_act = hidden_act self.hidden_dropout_prob = hidden_dropout_prob self.attention_probs_dropout_prob = attention_probs_dropout_prob self.initializer_range = initializer_range self.layer_norm_eps = layer_norm_eps self.image_size = image_size self.patch_size = patch_size self.num_channels = num_channels self.qkv_bias = qkv_bias self.stage_names = ["stem"] + [f"stage{idx}" for idx in range(1, num_hidden_layers + 1)] self._out_features, self._out_indices = get_aligned_output_features_output_indices( out_features=out_features, out_indices=out_indices, stage_names=self.stage_names )