Spaces:
Running
on
T4
Running
on
T4
Grounded-Segment-Anything
/
transformers_4_35_0
/models
/conditional_detr
/configuration_conditional_detr.py
# 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. | |
""" Conditional 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 ..auto import CONFIG_MAPPING | |
logger = logging.get_logger(__name__) | |
CONDITIONAL_DETR_PRETRAINED_CONFIG_ARCHIVE_MAP = { | |
"microsoft/conditional-detr-resnet-50": ( | |
"https://huggingface.co/microsoft/conditional-detr-resnet-50/resolve/main/config.json" | |
), | |
} | |
class ConditionalDetrConfig(PretrainedConfig): | |
r""" | |
This is the configuration class to store the configuration of a [`ConditionalDetrModel`]. It is used to instantiate | |
a Conditional 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 Conditional DETR | |
[microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-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 | |
[`ConditionalDetrModel`] 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 convolutional backbone to use in case `use_timm_backbone` = `True`. Supports any convolutional | |
backbone from the timm package. For a list of all available models, see [this | |
page](https://rwightman.github.io/pytorch-image-models/#load-a-pretrained-model). | |
use_pretrained_backbone (`bool`, *optional*, defaults to `True`): | |
Whether to use pretrained weights for the backbone. Only supported when `use_timm_backbone` = `True`. | |
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. | |
focal_alpha (`float`, *optional*, defaults to 0.25): | |
Alpha parameter in the focal loss. | |
Examples: | |
```python | |
>>> from transformers import ConditionalDetrConfig, ConditionalDetrModel | |
>>> # Initializing a Conditional DETR microsoft/conditional-detr-resnet-50 style configuration | |
>>> configuration = ConditionalDetrConfig() | |
>>> # Initializing a model (with random weights) from the microsoft/conditional-detr-resnet-50 style configuration | |
>>> model = ConditionalDetrModel(configuration) | |
>>> # Accessing the model configuration | |
>>> configuration = model.config | |
```""" | |
model_type = "conditional_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=300, | |
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, | |
dilation=False, | |
class_cost=2, | |
bbox_cost=5, | |
giou_cost=2, | |
mask_loss_coefficient=1, | |
dice_loss_coefficient=1, | |
cls_loss_coefficient=2, | |
bbox_loss_coefficient=5, | |
giou_loss_coefficient=2, | |
focal_alpha=0.25, | |
**kwargs, | |
): | |
if backbone_config is not None and use_timm_backbone: | |
raise ValueError("You can't specify both `backbone_config` and `use_timm_backbone`.") | |
if not use_timm_backbone: | |
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) | |
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.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.cls_loss_coefficient = cls_loss_coefficient | |
self.bbox_loss_coefficient = bbox_loss_coefficient | |
self.giou_loss_coefficient = giou_loss_coefficient | |
self.focal_alpha = focal_alpha | |
super().__init__(is_encoder_decoder=is_encoder_decoder, **kwargs) | |
def num_attention_heads(self) -> int: | |
return self.encoder_attention_heads | |
def hidden_size(self) -> int: | |
return self.d_model | |
class ConditionalDetrOnnxConfig(OnnxConfig): | |
torch_onnx_minimum_version = version.parse("1.11") | |
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"}), | |
] | |
) | |
def atol_for_validation(self) -> float: | |
return 1e-5 | |
def default_onnx_opset(self) -> int: | |
return 12 | |