# coding=utf-8 # Copyright 2022 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. """YOLOS model configuration""" from collections import OrderedDict from typing import Mapping from packaging import version from ...configuration_utils import PretrainedConfig from ...onnx import OnnxConfig from ...utils import logging logger = logging.get_logger(__name__) class YolosConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`YolosModel`]. It is used to instantiate a YOLOS 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 YOLOS [hustvl/yolos-base](https://huggingface.co/hustvl/yolos-base) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: 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. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) 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 probability 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. image_size (`List[int]`, *optional*, defaults to `[512, 864]`): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. num_detection_tokens (`int`, *optional*, defaults to 100): The number of detection tokens. use_mid_position_embeddings (`bool`, *optional*, defaults to `True`): Whether to use the mid-layer position encodings. auxiliary_loss (`bool`, *optional*, defaults to `False`): Whether auxiliary decoding losses (loss at each decoder layer) are to be used. class_cost (`float`, *optional*, defaults to 1): Relative weight of the classification error in the Hungarian matching cost. bbox_cost (`float`, *optional*, defaults to 5): Relative weight of the L1 error of the bounding box coordinates in the Hungarian matching cost. giou_cost (`float`, *optional*, defaults to 2): Relative weight of the generalized IoU loss of the bounding box in the Hungarian matching cost. bbox_loss_coefficient (`float`, *optional*, defaults to 5): Relative weight of the L1 bounding box loss in the object detection loss. giou_loss_coefficient (`float`, *optional*, defaults to 2): Relative weight of the generalized IoU loss in the object detection loss. eos_coefficient (`float`, *optional*, defaults to 0.1): Relative classification weight of the 'no-object' class in the object detection loss. Example: ```python >>> from transformers import YolosConfig, YolosModel >>> # Initializing a YOLOS hustvl/yolos-base style configuration >>> configuration = YolosConfig() >>> # Initializing a model (with random weights) from the hustvl/yolos-base style configuration >>> model = YolosModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "yolos" def __init__( self, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act="gelu", hidden_dropout_prob=0.0, attention_probs_dropout_prob=0.0, initializer_range=0.02, layer_norm_eps=1e-12, image_size=[512, 864], patch_size=16, num_channels=3, qkv_bias=True, num_detection_tokens=100, use_mid_position_embeddings=True, auxiliary_loss=False, class_cost=1, bbox_cost=5, giou_cost=2, bbox_loss_coefficient=5, giou_loss_coefficient=2, eos_coefficient=0.1, **kwargs, ): super().__init__(**kwargs) self.hidden_size = hidden_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads self.intermediate_size = intermediate_size 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.num_detection_tokens = num_detection_tokens self.use_mid_position_embeddings = use_mid_position_embeddings self.auxiliary_loss = auxiliary_loss # Hungarian matcher self.class_cost = class_cost self.bbox_cost = bbox_cost self.giou_cost = giou_cost # Loss coefficients self.bbox_loss_coefficient = bbox_loss_coefficient self.giou_loss_coefficient = giou_loss_coefficient self.eos_coefficient = eos_coefficient class YolosOnnxConfig(OnnxConfig): torch_onnx_minimum_version = version.parse("1.11") @property def inputs(self) -> Mapping[str, Mapping[int, str]]: return OrderedDict( [ ("pixel_values", {0: "batch", 1: "num_channels", 2: "height", 3: "width"}), ] ) @property def atol_for_validation(self) -> float: return 1e-4 @property def default_onnx_opset(self) -> int: return 12 __all__ = ["YolosConfig", "YolosOnnxConfig"]