File size: 13,761 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 |
# 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.
"""SAM model configuration"""
from ...configuration_utils import PretrainedConfig
from ...utils import logging
logger = logging.get_logger(__name__)
class SamPromptEncoderConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`SamPromptEncoder`]. The [`SamPromptEncoder`]
module is used to encode the input 2D points and bounding boxes. Instantiating a configuration defaults will yield
a similar configuration to that of the SAM-vit-h
[facebook/sam-vit-huge](https://huggingface.co/facebook/sam-vit-huge) 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 256):
Dimensionality of the hidden states.
image_size (`int`, *optional*, defaults to 1024):
The expected output resolution of the image.
patch_size (`int`, *optional*, defaults to 16):
The size (resolution) of each patch.
mask_input_channels (`int`, *optional*, defaults to 16):
The number of channels to be fed to the `MaskDecoder` module.
num_point_embeddings (`int`, *optional*, defaults to 4):
The number of point embeddings to be used.
hidden_act (`str`, *optional*, defaults to `"gelu"`):
The non-linear activation function in the encoder and pooler.
"""
def __init__(
self,
hidden_size=256,
image_size=1024,
patch_size=16,
mask_input_channels=16,
num_point_embeddings=4,
hidden_act="gelu",
layer_norm_eps=1e-6,
**kwargs,
):
super().__init__(**kwargs)
self.hidden_size = hidden_size
self.image_size = image_size
self.patch_size = patch_size
self.image_embedding_size = image_size // patch_size
self.mask_input_channels = mask_input_channels
self.num_point_embeddings = num_point_embeddings
self.hidden_act = hidden_act
self.layer_norm_eps = layer_norm_eps
class SamMaskDecoderConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`SamMaskDecoder`]. It is used to instantiate a SAM
mask decoder to the specified arguments, defining the model architecture. Instantiating a configuration defaults
will yield a similar configuration to that of the SAM-vit-h
[facebook/sam-vit-huge](https://huggingface.co/facebook/sam-vit-huge) 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 256):
Dimensionality of the hidden states.
hidden_act (`str`, *optional*, defaults to `"relu"`):
The non-linear activation function used inside the `SamMaskDecoder` module.
mlp_dim (`int`, *optional*, defaults to 2048):
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
num_hidden_layers (`int`, *optional*, defaults to 2):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 8):
Number of attention heads for each attention layer in the Transformer encoder.
attention_downsample_rate (`int`, *optional*, defaults to 2):
The downsampling rate of the attention layer.
num_multimask_outputs (`int`, *optional*, defaults to 3):
The number of outputs from the `SamMaskDecoder` module. In the Segment Anything paper, this is set to 3.
iou_head_depth (`int`, *optional*, defaults to 3):
The number of layers in the IoU head module.
iou_head_hidden_dim (`int`, *optional*, defaults to 256):
The dimensionality of the hidden states in the IoU head module.
layer_norm_eps (`float`, *optional*, defaults to 1e-06):
The epsilon used by the layer normalization layers.
"""
def __init__(
self,
hidden_size=256,
hidden_act="relu",
mlp_dim=2048,
num_hidden_layers=2,
num_attention_heads=8,
attention_downsample_rate=2,
num_multimask_outputs=3,
iou_head_depth=3,
iou_head_hidden_dim=256,
layer_norm_eps=1e-6,
**kwargs,
):
super().__init__(**kwargs)
self.hidden_size = hidden_size
self.hidden_act = hidden_act
self.mlp_dim = mlp_dim
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.attention_downsample_rate = attention_downsample_rate
self.num_multimask_outputs = num_multimask_outputs
self.iou_head_depth = iou_head_depth
self.iou_head_hidden_dim = iou_head_hidden_dim
self.layer_norm_eps = layer_norm_eps
class SamVisionConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`SamVisionModel`]. It is used to instantiate a SAM
vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration
defaults will yield a similar configuration to that of the SAM ViT-h
[facebook/sam-vit-huge](https://huggingface.co/facebook/sam-vit-huge) 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.
output_channels (`int`, *optional*, defaults to 256):
Dimensionality of the output channels in the Patch Encoder.
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.
num_channels (`int`, *optional*, defaults to 3):
Number of channels in the input image.
image_size (`int`, *optional*, defaults to 1024):
Expected resolution. Target size of the resized input image.
patch_size (`int`, *optional*, defaults to 16):
Size of the patches to be extracted from the input image.
hidden_act (`str`, *optional*, defaults to `"gelu"`):
The non-linear activation function (function or string)
layer_norm_eps (`float`, *optional*, defaults to 1e-06):
The epsilon used by the layer normalization layers.
attention_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio for the attention probabilities.
initializer_range (`float`, *optional*, defaults to 1e-10):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
qkv_bias (`bool`, *optional*, defaults to `True`):
Whether to add a bias to query, key, value projections.
mlp_ratio (`float`, *optional*, defaults to 4.0):
Ratio of mlp hidden dim to embedding dim.
use_abs_pos (`bool`, *optional*, defaults to `True`):
Whether to use absolute position embedding.
use_rel_pos (`bool`, *optional*, defaults to `True`):
Whether to use relative position embedding.
window_size (`int`, *optional*, defaults to 14):
Window size for relative position.
global_attn_indexes (`List[int]`, *optional*, defaults to `[2, 5, 8, 11]`):
The indexes of the global attention layers.
num_pos_feats (`int`, *optional*, defaults to 128):
The dimensionality of the position embedding.
mlp_dim (`int`, *optional*):
The dimensionality of the MLP layer in the Transformer encoder. If `None`, defaults to `mlp_ratio *
hidden_size`.
"""
def __init__(
self,
hidden_size=768,
output_channels=256,
num_hidden_layers=12,
num_attention_heads=12,
num_channels=3,
image_size=1024,
patch_size=16,
hidden_act="gelu",
layer_norm_eps=1e-06,
attention_dropout=0.0,
initializer_range=1e-10,
qkv_bias=True,
mlp_ratio=4.0,
use_abs_pos=True,
use_rel_pos=True,
window_size=14,
global_attn_indexes=[2, 5, 8, 11],
num_pos_feats=128,
mlp_dim=None,
**kwargs,
):
super().__init__(**kwargs)
self.hidden_size = hidden_size
self.output_channels = output_channels
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.num_channels = num_channels
self.image_size = image_size
self.patch_size = patch_size
self.hidden_act = hidden_act
self.layer_norm_eps = layer_norm_eps
self.attention_dropout = attention_dropout
self.initializer_range = initializer_range
self.qkv_bias = qkv_bias
self.mlp_ratio = mlp_ratio
self.use_abs_pos = use_abs_pos
self.use_rel_pos = use_rel_pos
self.window_size = window_size
self.global_attn_indexes = global_attn_indexes
self.num_pos_feats = num_pos_feats
self.mlp_dim = int(hidden_size * mlp_ratio) if mlp_dim is None else mlp_dim
class SamConfig(PretrainedConfig):
r"""
[`SamConfig`] is the configuration class to store the configuration of a [`SamModel`]. It is used to instantiate a
SAM model according to the specified arguments, defining the vision model, prompt-encoder model and mask decoder
configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the
SAM-ViT-H [facebook/sam-vit-huge](https://huggingface.co/facebook/sam-vit-huge) architecture.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
vision_config (Union[`dict`, `SamVisionConfig`], *optional*):
Dictionary of configuration options used to initialize [`SamVisionConfig`].
prompt_encoder_config (Union[`dict`, `SamPromptEncoderConfig`], *optional*):
Dictionary of configuration options used to initialize [`SamPromptEncoderConfig`].
mask_decoder_config (Union[`dict`, `SamMaskDecoderConfig`], *optional*):
Dictionary of configuration options used to initialize [`SamMaskDecoderConfig`].
kwargs (*optional*):
Dictionary of keyword arguments.
Example:
```python
>>> from transformers import (
... SamVisionConfig,
... SamPromptEncoderConfig,
... SamMaskDecoderConfig,
... SamModel,
... )
>>> # Initializing a SamConfig with `"facebook/sam-vit-huge"` style configuration
>>> configuration = SamConfig()
>>> # Initializing a SamModel (with random weights) from the `"facebook/sam-vit-huge"` style configuration
>>> model = SamModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
>>> # We can also initialize a SamConfig from a SamVisionConfig, SamPromptEncoderConfig, and SamMaskDecoderConfig
>>> # Initializing SAM vision, SAM Q-Former and language model configurations
>>> vision_config = SamVisionConfig()
>>> prompt_encoder_config = SamPromptEncoderConfig()
>>> mask_decoder_config = SamMaskDecoderConfig()
>>> config = SamConfig(vision_config, prompt_encoder_config, mask_decoder_config)
```"""
model_type = "sam"
def __init__(
self,
vision_config=None,
prompt_encoder_config=None,
mask_decoder_config=None,
initializer_range=0.02,
**kwargs,
):
super().__init__(**kwargs)
vision_config = vision_config if vision_config is not None else {}
prompt_encoder_config = prompt_encoder_config if prompt_encoder_config is not None else {}
mask_decoder_config = mask_decoder_config if mask_decoder_config is not None else {}
if isinstance(vision_config, SamVisionConfig):
vision_config = vision_config.to_dict()
if isinstance(prompt_encoder_config, SamPromptEncoderConfig):
prompt_encoder_config = prompt_encoder_config.to_dict()
if isinstance(mask_decoder_config, SamMaskDecoderConfig):
mask_decoder_config = mask_decoder_config.to_dict()
self.vision_config = SamVisionConfig(**vision_config)
self.prompt_encoder_config = SamPromptEncoderConfig(**prompt_encoder_config)
self.mask_decoder_config = SamMaskDecoderConfig(**mask_decoder_config)
self.initializer_range = initializer_range
|