File size: 13,486 Bytes
d1ceb73 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 |
# coding=utf-8
# Copyright 2021 Facebook AI Research 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.
"""DETR 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
from ...utils.backbone_utils import verify_backbone_config_arguments
from ..auto import CONFIG_MAPPING
logger = logging.get_logger(__name__)
class DetrConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`DetrModel`]. It is used to instantiate a DETR
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 DETR
[facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) architecture.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
use_timm_backbone (`bool`, *optional*, defaults to `True`):
Whether or not to use the `timm` library for the backbone. If set to `False`, will use the [`AutoBackbone`]
API.
backbone_config (`PretrainedConfig` or `dict`, *optional*):
The configuration of the backbone model. Only used in case `use_timm_backbone` is set to `False` in which
case it will default to `ResNetConfig()`.
num_channels (`int`, *optional*, defaults to 3):
The number of input channels.
num_queries (`int`, *optional*, defaults to 100):
Number of object queries, i.e. detection slots. This is the maximal number of objects [`DetrModel`] can
detect in a single image. For COCO, we recommend 100 queries.
d_model (`int`, *optional*, defaults to 256):
Dimension of the layers.
encoder_layers (`int`, *optional*, defaults to 6):
Number of encoder layers.
decoder_layers (`int`, *optional*, defaults to 6):
Number of decoder layers.
encoder_attention_heads (`int`, *optional*, defaults to 8):
Number of attention heads for each attention layer in the Transformer encoder.
decoder_attention_heads (`int`, *optional*, defaults to 8):
Number of attention heads for each attention layer in the Transformer decoder.
decoder_ffn_dim (`int`, *optional*, defaults to 2048):
Dimension of the "intermediate" (often named feed-forward) layer in decoder.
encoder_ffn_dim (`int`, *optional*, defaults to 2048):
Dimension of the "intermediate" (often named feed-forward) layer in decoder.
activation_function (`str` or `function`, *optional*, defaults to `"relu"`):
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
`"relu"`, `"silu"` and `"gelu_new"` are supported.
dropout (`float`, *optional*, defaults to 0.1):
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
attention_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio for the attention probabilities.
activation_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio for activations inside the fully connected layer.
init_std (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
init_xavier_std (`float`, *optional*, defaults to 1):
The scaling factor used for the Xavier initialization gain in the HM Attention map module.
encoder_layerdrop (`float`, *optional*, defaults to 0.0):
The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
for more details.
decoder_layerdrop (`float`, *optional*, defaults to 0.0):
The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
for more details.
auxiliary_loss (`bool`, *optional*, defaults to `False`):
Whether auxiliary decoding losses (loss at each decoder layer) are to be used.
position_embedding_type (`str`, *optional*, defaults to `"sine"`):
Type of position embeddings to be used on top of the image features. One of `"sine"` or `"learned"`.
backbone (`str`, *optional*, defaults to `"resnet50"`):
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*, `True`):
Whether to use pretrained weights for the backbone.
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.
dilation (`bool`, *optional*, defaults to `False`):
Whether to replace stride with dilation in the last convolutional block (DC5). Only supported when
`use_timm_backbone` = `True`.
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.
mask_loss_coefficient (`float`, *optional*, defaults to 1):
Relative weight of the Focal loss in the panoptic segmentation loss.
dice_loss_coefficient (`float`, *optional*, defaults to 1):
Relative weight of the DICE/F-1 loss in the panoptic segmentation loss.
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.
Examples:
```python
>>> from transformers import DetrConfig, DetrModel
>>> # Initializing a DETR facebook/detr-resnet-50 style configuration
>>> configuration = DetrConfig()
>>> # Initializing a model (with random weights) from the facebook/detr-resnet-50 style configuration
>>> model = DetrModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "detr"
keys_to_ignore_at_inference = ["past_key_values"]
attribute_map = {
"hidden_size": "d_model",
"num_attention_heads": "encoder_attention_heads",
}
def __init__(
self,
use_timm_backbone=True,
backbone_config=None,
num_channels=3,
num_queries=100,
encoder_layers=6,
encoder_ffn_dim=2048,
encoder_attention_heads=8,
decoder_layers=6,
decoder_ffn_dim=2048,
decoder_attention_heads=8,
encoder_layerdrop=0.0,
decoder_layerdrop=0.0,
is_encoder_decoder=True,
activation_function="relu",
d_model=256,
dropout=0.1,
attention_dropout=0.0,
activation_dropout=0.0,
init_std=0.02,
init_xavier_std=1.0,
auxiliary_loss=False,
position_embedding_type="sine",
backbone="resnet50",
use_pretrained_backbone=True,
backbone_kwargs=None,
dilation=False,
class_cost=1,
bbox_cost=5,
giou_cost=2,
mask_loss_coefficient=1,
dice_loss_coefficient=1,
bbox_loss_coefficient=5,
giou_loss_coefficient=2,
eos_coefficient=0.1,
**kwargs,
):
# We default to values which were previously hard-coded in the model. This enables configurability of the config
# while keeping the default behavior the same.
if use_timm_backbone and backbone_kwargs is None:
backbone_kwargs = {}
if dilation:
backbone_kwargs["output_stride"] = 16
backbone_kwargs["out_indices"] = [1, 2, 3, 4]
backbone_kwargs["in_chans"] = num_channels
# Backwards compatibility
elif not use_timm_backbone and backbone in (None, "resnet50"):
if backbone_config is None:
logger.info("`backbone_config` is `None`. Initializing the config with the default `ResNet` backbone.")
backbone_config = CONFIG_MAPPING["resnet"](out_features=["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)
backbone = None
# set timm attributes to None
dilation = None
verify_backbone_config_arguments(
use_timm_backbone=use_timm_backbone,
use_pretrained_backbone=use_pretrained_backbone,
backbone=backbone,
backbone_config=backbone_config,
backbone_kwargs=backbone_kwargs,
)
self.use_timm_backbone = use_timm_backbone
self.backbone_config = backbone_config
self.num_channels = num_channels
self.num_queries = num_queries
self.d_model = d_model
self.encoder_ffn_dim = encoder_ffn_dim
self.encoder_layers = encoder_layers
self.encoder_attention_heads = encoder_attention_heads
self.decoder_ffn_dim = decoder_ffn_dim
self.decoder_layers = decoder_layers
self.decoder_attention_heads = decoder_attention_heads
self.dropout = dropout
self.attention_dropout = attention_dropout
self.activation_dropout = activation_dropout
self.activation_function = activation_function
self.init_std = init_std
self.init_xavier_std = init_xavier_std
self.encoder_layerdrop = encoder_layerdrop
self.decoder_layerdrop = decoder_layerdrop
self.num_hidden_layers = encoder_layers
self.auxiliary_loss = auxiliary_loss
self.position_embedding_type = position_embedding_type
self.backbone = backbone
self.use_pretrained_backbone = use_pretrained_backbone
self.backbone_kwargs = backbone_kwargs
self.dilation = dilation
# Hungarian matcher
self.class_cost = class_cost
self.bbox_cost = bbox_cost
self.giou_cost = giou_cost
# Loss coefficients
self.mask_loss_coefficient = mask_loss_coefficient
self.dice_loss_coefficient = dice_loss_coefficient
self.bbox_loss_coefficient = bbox_loss_coefficient
self.giou_loss_coefficient = giou_loss_coefficient
self.eos_coefficient = eos_coefficient
super().__init__(is_encoder_decoder=is_encoder_decoder, **kwargs)
@property
def num_attention_heads(self) -> int:
return self.encoder_attention_heads
@property
def hidden_size(self) -> int:
return self.d_model
@classmethod
def from_backbone_config(cls, backbone_config: PretrainedConfig, **kwargs):
"""Instantiate a [`DetrConfig`] (or a derived class) from a pre-trained backbone model configuration.
Args:
backbone_config ([`PretrainedConfig`]):
The backbone configuration.
Returns:
[`DetrConfig`]: An instance of a configuration object
"""
return cls(backbone_config=backbone_config, **kwargs)
class DetrOnnxConfig(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"}),
("pixel_mask", {0: "batch"}),
]
)
@property
def atol_for_validation(self) -> float:
return 1e-5
@property
def default_onnx_opset(self) -> int:
return 12
|