# 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. """ UperNet model configuration""" from ...configuration_utils import PretrainedConfig from ...utils import logging from ..auto.configuration_auto import CONFIG_MAPPING logger = logging.get_logger(__name__) class UperNetConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of an [`UperNetForSemanticSegmentation`]. It is used to instantiate an UperNet 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 UperNet [openmmlab/upernet-convnext-tiny](https://huggingface.co/openmmlab/upernet-convnext-tiny) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: backbone_config (`PretrainedConfig` or `dict`, *optional*, defaults to `ResNetConfig()`): The configuration of the backbone model. backbone (`str`, *optional*): Name of backbone to use when `backbone_config` is `None`. If `use_pretrained_backbone` is `True`, this will load the corresponding pretrained weights from the timm or transformers library. If `use_pretrained_backbone` is `False`, this loads the backbone's config and uses that to initialize the backbone with random weights. use_pretrained_backbone (`bool`, *optional*, `False`): Whether to use pretrained weights for the backbone. use_timm_backbone (`bool`, *optional*, `False`): Whether to load `backbone` from the timm library. If `False`, the backbone is loaded from the transformers library. backbone_kwargs (`dict`, *optional*): Keyword arguments to be passed to AutoBackbone when loading from a checkpoint e.g. `{'out_indices': (0, 1, 2, 3)}`. Cannot be specified if `backbone_config` is set. hidden_size (`int`, *optional*, defaults to 512): The number of hidden units in the convolutional layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. pool_scales (`Tuple[int]`, *optional*, defaults to `[1, 2, 3, 6]`): Pooling scales used in Pooling Pyramid Module applied on the last feature map. use_auxiliary_head (`bool`, *optional*, defaults to `True`): Whether to use an auxiliary head during training. auxiliary_loss_weight (`float`, *optional*, defaults to 0.4): Weight of the cross-entropy loss of the auxiliary head. auxiliary_channels (`int`, *optional*, defaults to 256): Number of channels to use in the auxiliary head. auxiliary_num_convs (`int`, *optional*, defaults to 1): Number of convolutional layers to use in the auxiliary head. auxiliary_concat_input (`bool`, *optional*, defaults to `False`): Whether to concatenate the output of the auxiliary head with the input before the classification layer. loss_ignore_index (`int`, *optional*, defaults to 255): The index that is ignored by the loss function. Examples: ```python >>> from transformers import UperNetConfig, UperNetForSemanticSegmentation >>> # Initializing a configuration >>> configuration = UperNetConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = UperNetForSemanticSegmentation(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```""" model_type = "upernet" def __init__( self, backbone_config=None, backbone=None, use_pretrained_backbone=False, use_timm_backbone=False, backbone_kwargs=None, hidden_size=512, initializer_range=0.02, pool_scales=[1, 2, 3, 6], use_auxiliary_head=True, auxiliary_loss_weight=0.4, auxiliary_in_channels=384, auxiliary_channels=256, auxiliary_num_convs=1, auxiliary_concat_input=False, loss_ignore_index=255, **kwargs, ): super().__init__(**kwargs) if use_pretrained_backbone: raise ValueError("Pretrained backbones are not supported yet.") if backbone_config is not None and backbone is not None: raise ValueError("You can't specify both `backbone` and `backbone_config`.") if backbone_config is None and backbone is None: logger.info("`backbone_config` is `None`. Initializing the config with the default `ResNet` backbone.") backbone_config = CONFIG_MAPPING["resnet"](out_features=["stage1", "stage2", "stage3", "stage4"]) elif isinstance(backbone_config, dict): backbone_model_type = backbone_config.get("model_type") config_class = CONFIG_MAPPING[backbone_model_type] backbone_config = config_class.from_dict(backbone_config) if backbone_kwargs is not None and backbone_kwargs and backbone_config is not None: raise ValueError("You can't specify both `backbone_kwargs` and `backbone_config`.") self.backbone_config = backbone_config self.backbone = backbone self.use_pretrained_backbone = use_pretrained_backbone self.use_timm_backbone = use_timm_backbone self.backbone_kwargs = backbone_kwargs self.hidden_size = hidden_size self.initializer_range = initializer_range self.pool_scales = pool_scales self.use_auxiliary_head = use_auxiliary_head self.auxiliary_loss_weight = auxiliary_loss_weight self.auxiliary_in_channels = auxiliary_in_channels self.auxiliary_channels = auxiliary_channels self.auxiliary_num_convs = auxiliary_num_convs self.auxiliary_concat_input = auxiliary_concat_input self.loss_ignore_index = loss_ignore_index