File size: 12,356 Bytes
fabf416 1afcb0c fabf416 |
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 |
"""
Autoencoder configuration for Hugging Face Transformers.
"""
from transformers import PretrainedConfig
from typing import List, Optional
# Support both package-relative and flat import in HF remote code context
try:
from . import __version__ as _pkg_version # type: ignore
except Exception: # pragma: no cover
_pkg_version = None
class AutoencoderConfig(PretrainedConfig):
"""
Configuration class for Autoencoder models.
This configuration class stores the configuration of an autoencoder model. It is used to instantiate
an autoencoder model according to the specified arguments, defining the model architecture.
Args:
input_dim (int, optional): Dimensionality of the input data. Defaults to 784.
hidden_dims (List[int], optional): List of hidden layer dimensions for the encoder.
The decoder will use the reverse of this list. Defaults to [512, 256, 128].
latent_dim (int, optional): Dimensionality of the latent space. Defaults to 64.
activation (str, optional): Activation function to use. Options: "relu", "tanh", "sigmoid",
"leaky_relu", "gelu", "swish", "silu", "elu", "prelu", "relu6", "hardtanh",
"hardsigmoid", "hardswish", "mish", "softplus", "softsign", "tanhshrink", "threshold".
Defaults to "relu".
dropout_rate (float, optional): Dropout rate for regularization. Defaults to 0.1.
use_batch_norm (bool, optional): Whether to use batch normalization. Defaults to True.
tie_weights (bool, optional): Whether to tie encoder and decoder weights. Defaults to False.
reconstruction_loss (str, optional): Type of reconstruction loss. Options: "mse", "bce", "l1",
"huber", "smooth_l1", "kl_div", "cosine", "focal", "dice", "tversky", "ssim", "perceptual".
Defaults to "mse".
autoencoder_type (str, optional): Type of autoencoder architecture. Options: "classic",
"variational", "beta_vae", "denoising", "sparse", "contractive", "recurrent". Defaults to "classic".
beta (float, optional): Beta parameter for beta-VAE. Defaults to 1.0.
temperature (float, optional): Temperature parameter for Gumbel softmax or other operations. Defaults to 1.0.
noise_factor (float, optional): Noise factor for denoising autoencoders. Defaults to 0.1.
rnn_type (str, optional): Type of RNN cell for recurrent autoencoders. Options: "lstm", "gru", "rnn".
Defaults to "lstm".
num_layers (int, optional): Number of RNN layers for recurrent autoencoders. Defaults to 2.
bidirectional (bool, optional): Whether to use bidirectional RNN for encoding. Defaults to True.
sequence_length (int, optional): Fixed sequence length. If None, supports variable length sequences.
Defaults to None.
teacher_forcing_ratio (float, optional): Ratio of teacher forcing during training for recurrent decoders.
Defaults to 0.5.
use_learnable_preprocessing (bool, optional): Whether to use learnable preprocessing. Defaults to False.
preprocessing_type (str, optional): Type of learnable preprocessing. Options: "none", "neural_scaler",
"normalizing_flow", "minmax_scaler", "robust_scaler", "yeo_johnson". Defaults to "none".
preprocessing_hidden_dim (int, optional): Hidden dimension for preprocessing networks. Defaults to 64.
preprocessing_num_layers (int, optional): Number of layers in preprocessing networks. Defaults to 2.
learn_inverse_preprocessing (bool, optional): Whether to learn inverse preprocessing for reconstruction.
Defaults to True.
flow_coupling_layers (int, optional): Number of coupling layers for normalizing flows. Defaults to 4.
**kwargs: Additional keyword arguments passed to the parent class.
"""
model_type = "autoencoder"
def __init__(
self,
input_dim: int = 784,
hidden_dims: List[int] = None,
latent_dim: int = 64,
activation: str = "relu",
dropout_rate: float = 0.1,
use_batch_norm: bool = True,
tie_weights: bool = False,
reconstruction_loss: str = "mse",
autoencoder_type: str = "classic",
beta: float = 1.0,
temperature: float = 1.0,
noise_factor: float = 0.1,
# Recurrent autoencoder parameters
rnn_type: str = "lstm",
num_layers: int = 2,
bidirectional: bool = True,
sequence_length: Optional[int] = None,
teacher_forcing_ratio: float = 0.5,
# Deep learning preprocessing parameters
use_learnable_preprocessing: bool = False,
preprocessing_type: str = "none",
preprocessing_hidden_dim: int = 64,
preprocessing_num_layers: int = 2,
learn_inverse_preprocessing: bool = True,
flow_coupling_layers: int = 4,
**kwargs,
):
# Validate parameters
if hidden_dims is None:
hidden_dims = [512, 256, 128]
# Extended activation functions
valid_activations = [
"relu", "tanh", "sigmoid", "leaky_relu", "gelu", "swish", "silu",
"elu", "prelu", "relu6", "hardtanh", "hardsigmoid", "hardswish",
"mish", "softplus", "softsign", "tanhshrink", "threshold"
]
if activation not in valid_activations:
raise ValueError(
f"`activation` must be one of {valid_activations}, got {activation}."
)
# Extended loss functions
valid_losses = [
"mse", "bce", "l1", "huber", "smooth_l1", "kl_div", "cosine",
"focal", "dice", "tversky", "ssim", "perceptual"
]
if reconstruction_loss not in valid_losses:
raise ValueError(
f"`reconstruction_loss` must be one of {valid_losses}, got {reconstruction_loss}."
)
# Autoencoder types
valid_types = ["classic", "variational", "beta_vae", "denoising", "sparse", "contractive", "recurrent"]
if autoencoder_type not in valid_types:
raise ValueError(
f"`autoencoder_type` must be one of {valid_types}, got {autoencoder_type}."
)
# RNN types for recurrent autoencoders
valid_rnn_types = ["lstm", "gru", "rnn"]
if rnn_type not in valid_rnn_types:
raise ValueError(
f"`rnn_type` must be one of {valid_rnn_types}, got {rnn_type}."
)
if not (0.0 <= dropout_rate <= 1.0):
raise ValueError(f"`dropout_rate` must be between 0.0 and 1.0, got {dropout_rate}.")
if input_dim <= 0:
raise ValueError(f"`input_dim` must be positive, got {input_dim}.")
if latent_dim <= 0:
raise ValueError(f"`latent_dim` must be positive, got {latent_dim}.")
if not all(dim > 0 for dim in hidden_dims):
raise ValueError("All dimensions in `hidden_dims` must be positive.")
if beta <= 0:
raise ValueError(f"`beta` must be positive, got {beta}.")
if num_layers <= 0:
raise ValueError(f"`num_layers` must be positive, got {num_layers}.")
if not (0.0 <= teacher_forcing_ratio <= 1.0):
raise ValueError(f"`teacher_forcing_ratio` must be between 0.0 and 1.0, got {teacher_forcing_ratio}.")
if sequence_length is not None and sequence_length <= 0:
raise ValueError(f"`sequence_length` must be positive when specified, got {sequence_length}.")
# Preprocessing validation
valid_preprocessing = [
"none",
"neural_scaler",
"normalizing_flow",
"minmax_scaler",
"robust_scaler",
"yeo_johnson",
]
if preprocessing_type not in valid_preprocessing:
raise ValueError(
f"`preprocessing_type` must be one of {valid_preprocessing}, got {preprocessing_type}."
)
if preprocessing_hidden_dim <= 0:
raise ValueError(f"`preprocessing_hidden_dim` must be positive, got {preprocessing_hidden_dim}.")
if preprocessing_num_layers <= 0:
raise ValueError(f"`preprocessing_num_layers` must be positive, got {preprocessing_num_layers}.")
if flow_coupling_layers <= 0:
raise ValueError(f"`flow_coupling_layers` must be positive, got {flow_coupling_layers}.")
# Set configuration attributes
self.input_dim = input_dim
self.hidden_dims = hidden_dims
self.latent_dim = latent_dim
self.activation = activation
self.dropout_rate = dropout_rate
self.use_batch_norm = use_batch_norm
self.tie_weights = tie_weights
self.reconstruction_loss = reconstruction_loss
self.autoencoder_type = autoencoder_type
self.beta = beta
self.temperature = temperature
self.noise_factor = noise_factor
self.rnn_type = rnn_type
self.num_layers = num_layers
self.bidirectional = bidirectional
self.sequence_length = sequence_length
self.teacher_forcing_ratio = teacher_forcing_ratio
self.use_learnable_preprocessing = use_learnable_preprocessing
self.preprocessing_type = preprocessing_type
self.preprocessing_hidden_dim = preprocessing_hidden_dim
self.preprocessing_num_layers = preprocessing_num_layers
self.learn_inverse_preprocessing = learn_inverse_preprocessing
self.flow_coupling_layers = flow_coupling_layers
# Call parent constructor
super().__init__(**kwargs)
@property
def decoder_dims(self) -> List[int]:
"""Get decoder dimensions (reverse of encoder hidden dims)."""
return list(reversed(self.hidden_dims))
@property
def is_variational(self) -> bool:
"""Check if this is a variational autoencoder."""
return self.autoencoder_type in ["variational", "beta_vae"]
@property
def is_denoising(self) -> bool:
"""Check if this is a denoising autoencoder."""
return self.autoencoder_type == "denoising"
@property
def is_sparse(self) -> bool:
"""Check if this is a sparse autoencoder."""
return self.autoencoder_type == "sparse"
@property
def is_contractive(self) -> bool:
"""Check if this is a contractive autoencoder."""
return self.autoencoder_type == "contractive"
@property
def is_recurrent(self) -> bool:
"""Check if this is a recurrent autoencoder."""
return self.autoencoder_type == "recurrent"
@property
def rnn_hidden_size(self) -> int:
"""Get the RNN hidden size (same as latent_dim for recurrent AE)."""
return self.latent_dim
@property
def rnn_output_size(self) -> int:
"""Get the RNN output size considering bidirectionality."""
return self.latent_dim * (2 if self.bidirectional else 1)
@property
def has_preprocessing(self) -> bool:
"""Check if learnable preprocessing is enabled."""
return self.use_learnable_preprocessing and self.preprocessing_type != "none"
@property
def is_neural_scaler(self) -> bool:
"""Check if using neural scaler preprocessing."""
return self.preprocessing_type == "neural_scaler"
@property
def is_normalizing_flow(self) -> bool:
"""Check if using normalizing flow preprocessing."""
return self.preprocessing_type == "normalizing_flow"
@property
def is_minmax_scaler(self) -> bool:
"""Check if using learnable MinMax scaler preprocessing."""
return self.preprocessing_type == "minmax_scaler"
@property
def is_robust_scaler(self) -> bool:
"""Check if using learnable Robust scaler preprocessing."""
return self.preprocessing_type == "robust_scaler"
@property
def is_yeo_johnson(self) -> bool:
"""Check if using learnable Yeo-Johnson power transform preprocessing."""
return self.preprocessing_type == "yeo_johnson"
def to_dict(self):
"""
Serializes this instance to a Python dictionary.
"""
output = super().to_dict()
return output
|