File size: 8,354 Bytes
5cc6343 |
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 |
# coding=utf-8
# Copyright 2023 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.
""" DINOv2 model configuration"""
from collections import OrderedDict
from typing import Mapping
from packaging import version
from transformers.configuration_utils import PretrainedConfig
from transformers.onnx import OnnxConfig
from transformers.utils import logging
from transformers.utils.backbone_utils import (
BackboneConfigMixin,
get_aligned_output_features_output_indices,
)
logger = logging.get_logger(__name__)
class Dinov2Config(BackboneConfigMixin, PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`Dinov2Model`]. It is used to instantiate an
Dinov2 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 Dinov2
[google/dinov2-base-patch16-224](https://huggingface.co/google/dinov2-base-patch16-224) 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.
mlp_ratio (`int`, *optional*, defaults to 4):
Ratio of the hidden size of the MLPs relative to the `hidden_size`.
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-06):
The epsilon used by the layer normalization layers.
image_size (`int`, *optional*, defaults to 224):
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.
layerscale_value (`float`, *optional*, defaults to 1.0):
Initial value to use for layer scale.
drop_path_rate (`float`, *optional*, defaults to 0.0):
Stochastic depth rate per sample (when applied in the main path of residual layers).
use_swiglu_ffn (`bool`, *optional*, defaults to `False`):
Whether to use the SwiGLU feedforward neural network.
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.
apply_layernorm (`bool`, *optional*, defaults to `True`):
Whether to apply layer normalization to the feature maps in case the model is used as backbone.
reshape_hidden_states (`bool`, *optional*, defaults to `True`):
Whether to reshape the feature maps to 4D tensors of shape `(batch_size, hidden_size, height, width)` in
case the model is used as backbone. If `False`, the feature maps will be 3D tensors of shape `(batch_size,
seq_len, hidden_size)`.
Example:
```python
>>> from transformers import Dinov2Config, Dinov2Model
>>> # Initializing a Dinov2 dinov2-base-patch16-224 style configuration
>>> configuration = Dinov2Config()
>>> # Initializing a model (with random weights) from the dinov2-base-patch16-224 style configuration
>>> model = Dinov2Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "dinov2"
def __init__(
self,
hidden_size=768,
num_hidden_layers=12,
num_attention_heads=12,
mlp_ratio=4,
hidden_act="gelu",
hidden_dropout_prob=0.0,
attention_probs_dropout_prob=0.0,
initializer_range=0.02,
layer_norm_eps=1e-6,
image_size=224,
patch_size=16,
num_channels=3,
qkv_bias=True,
layerscale_value=1.0,
drop_path_rate=0.0,
use_swiglu_ffn=False,
out_features=None,
out_indices=None,
apply_layernorm=True,
reshape_hidden_states=True,
num_register_tokens=0,
**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.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.layerscale_value = layerscale_value
self.drop_path_rate = drop_path_rate
self.use_swiglu_ffn = use_swiglu_ffn
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,
)
self.apply_layernorm = apply_layernorm
self.reshape_hidden_states = reshape_hidden_states
# add register tokens
self.num_register_tokens = num_register_tokens
class Dinov2OnnxConfig(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
|