File size: 17,028 Bytes
8abd44b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 |
"""
Ready-to-use configuration templates for the block-based Autoencoder.
These helpers demonstrate how to assemble encoder_blocks and decoder_blocks
for a variety of architectures using the new block system. Each class extends
AutoencoderConfig and can be passed directly to AutoencoderModel.
Example:
from modeling_autoencoder import AutoencoderModel
from template import ClassicAutoencoderConfig
cfg = ClassicAutoencoderConfig(input_dim=784, latent_dim=64)
model = AutoencoderModel(cfg)
"""
from __future__ import annotations
from typing import List
# Support both package-relative and flat import
try:
from .configuration_autoencoder import (
AutoencoderConfig,
)
except Exception: # pragma: no cover
from configuration_autoencoder import (
AutoencoderConfig,
)
# ------------------------------- Helpers ------------------------------- #
def _linear_stack(input_dim: int, dims: List[int], activation: str = "relu", normalization: str = "batch", dropout: float = 0.0):
"""Build a list of Linear block dict configs mapping input_dim -> dims sequentially."""
blocks = []
prev = input_dim
for h in dims:
blocks.append({
"type": "linear",
"input_dim": prev,
"output_dim": h,
"activation": activation,
"normalization": normalization,
"dropout_rate": dropout,
"use_residual": False,
})
prev = h
return blocks
def _default_decoder(latent_dim: int, hidden: List[int], out_dim: int, activation: str = "relu", normalization: str = "batch", dropout: float = 0.0):
"""Linear decoder: latent_dim -> hidden -> out_dim (final layer identity)."""
blocks = _linear_stack(latent_dim, hidden + [out_dim], activation, normalization, dropout)
if blocks:
blocks[-1]["activation"] = "identity"
blocks[-1]["normalization"] = "none"
blocks[-1]["dropout_rate"] = 0.0
return blocks
# ---------------------------- Class-based templates ---------------------------- #
class ClassicAutoencoderConfig(AutoencoderConfig):
"""Classic dense autoencoder using Linear blocks.
Example:
cfg = ClassicAutoencoderConfig(input_dim=784, latent_dim=64)
"""
def __init__(self, input_dim: int = 784, latent_dim: int = 64, hidden: List[int] = (512, 256, 128), activation: str = "relu", dropout: float = 0.1, use_batch_norm: bool = True, **kwargs):
hidden = list(hidden)
norm = "batch" if use_batch_norm else "none"
enc = _linear_stack(input_dim, hidden, activation, norm, dropout)
dec = _default_decoder(latent_dim, list(reversed(hidden)), input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="classic",
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class VariationalAutoencoderConfig(AutoencoderConfig):
"""Variational autoencoder (MLP). Uses VariationalBlock in the model.
Example:
cfg = VariationalAutoencoderConfig(input_dim=784, latent_dim=32)
"""
def __init__(self, input_dim: int = 784, latent_dim: int = 32, hidden: List[int] = (512, 256, 128), activation: str = "relu", dropout: float = 0.1, use_batch_norm: bool = True, beta: float = 1.0, **kwargs):
hidden = list(hidden)
norm = "batch" if use_batch_norm else "none"
enc = _linear_stack(input_dim, hidden, activation, norm, dropout)
dec = _default_decoder(latent_dim, list(reversed(hidden)), input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="variational",
beta=beta,
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class TransformerAutoencoderConfig(AutoencoderConfig):
"""Transformer-style autoencoder with attention encoder and MLP decoder.
Works with (batch, input_dim) or (batch, time, input_dim).
Example:
cfg = TransformerAutoencoderConfig(input_dim=256, latent_dim=128)
"""
def __init__(self, input_dim: int = 256, latent_dim: int = 128, num_layers: int = 2, num_heads: int = 4, ffn_mult: int = 4, activation: str = "relu", dropout: float = 0.1, use_batch_norm: bool = False, **kwargs):
norm = "batch" if use_batch_norm else "none"
enc = []
enc.append({"type": "linear", "input_dim": input_dim, "output_dim": input_dim, "activation": activation, "normalization": norm, "dropout_rate": dropout})
for _ in range(num_layers):
enc.append({"type": "attention", "input_dim": input_dim, "num_heads": num_heads, "ffn_dim": ffn_mult * input_dim, "dropout_rate": dropout})
enc.append({"type": "linear", "input_dim": input_dim, "output_dim": input_dim, "activation": activation, "normalization": norm, "dropout_rate": dropout})
dec = _default_decoder(latent_dim, [input_dim], input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="classic",
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class RecurrentAutoencoderConfig(AutoencoderConfig):
"""Recurrent encoder (LSTM/GRU/RNN) for sequence data.
Expected input: (batch, time, input_dim). Decoder is MLP back to features per step.
Example:
cfg = RecurrentAutoencoderConfig(input_dim=128, latent_dim=64, rnn_type="lstm")
"""
def __init__(self, input_dim: int = 128, latent_dim: int = 64, rnn_type: str = "lstm", num_layers: int = 2, bidirectional: bool = False, activation: str = "relu", dropout: float = 0.1, use_batch_norm: bool = False, **kwargs):
norm = "batch" if use_batch_norm else "none"
enc = [{
"type": "recurrent",
"input_dim": input_dim,
"hidden_size": latent_dim,
"num_layers": num_layers,
"rnn_type": rnn_type,
"bidirectional": bidirectional,
"dropout_rate": dropout,
"output_dim": latent_dim,
}]
dec = _default_decoder(latent_dim, [max(latent_dim, input_dim)], input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="classic",
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class ConvolutionalAutoencoderConfig(AutoencoderConfig):
"""1D convolutional encoder for sequence data; decoder is per-step MLP.
Expected input: (batch, time, input_dim).
Example:
cfg = ConvolutionalAutoencoderConfig(input_dim=64, conv_channels=(64, 64))
"""
def __init__(self, input_dim: int = 64, latent_dim: int = 64, conv_channels: List[int] = (64, 64), kernel_size: int = 3, activation: str = "relu", dropout: float = 0.0, use_batch_norm: bool = True, **kwargs):
norm = "batch" if use_batch_norm else "none"
enc = []
prev = input_dim
for ch in conv_channels:
enc.append({"type": "conv1d", "input_dim": prev, "output_dim": ch, "kernel_size": kernel_size, "padding": "same", "activation": activation, "normalization": norm, "dropout_rate": dropout})
prev = ch
enc.append({"type": "linear", "input_dim": prev, "output_dim": latent_dim, "activation": activation, "normalization": norm, "dropout_rate": dropout})
dec = _default_decoder(latent_dim, [prev], input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="classic",
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class ConvAttentionAutoencoderConfig(AutoencoderConfig):
"""Mixed Conv + Attention encoder for sequence data.
Example:
cfg = ConvAttentionAutoencoderConfig(input_dim=64, latent_dim=64)
"""
def __init__(self, input_dim: int = 64, latent_dim: int = 64, conv_channels: List[int] = (64,), num_heads: int = 4, activation: str = "relu", dropout: float = 0.1, use_batch_norm: bool = True, **kwargs):
norm = "batch" if use_batch_norm else "none"
enc = []
prev = input_dim
for ch in conv_channels:
enc.append({"type": "conv1d", "input_dim": prev, "output_dim": ch, "kernel_size": 3, "padding": "same", "activation": activation, "normalization": norm, "dropout_rate": dropout})
prev = ch
enc.append({"type": "attention", "input_dim": prev, "num_heads": num_heads, "ffn_dim": 4 * prev, "dropout_rate": dropout})
enc.append({"type": "linear", "input_dim": prev, "output_dim": latent_dim, "activation": activation, "normalization": norm, "dropout_rate": dropout})
dec = _default_decoder(latent_dim, [prev], input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="classic",
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class LinearRecurrentAutoencoderConfig(AutoencoderConfig):
"""Linear down-projection then Recurrent encoder.
Example:
cfg = LinearRecurrentAutoencoderConfig(input_dim=256, latent_dim=64, rnn_type="gru")
"""
def __init__(self, input_dim: int = 256, latent_dim: int = 64, rnn_type: str = "gru", activation: str = "relu", dropout: float = 0.1, use_batch_norm: bool = False, **kwargs):
norm = "batch" if use_batch_norm else "none"
enc = [
{"type": "linear", "input_dim": input_dim, "output_dim": latent_dim, "activation": activation, "normalization": norm, "dropout_rate": dropout},
{"type": "recurrent", "input_dim": latent_dim, "hidden_size": latent_dim, "num_layers": 1, "rnn_type": rnn_type, "bidirectional": False, "dropout_rate": dropout, "output_dim": latent_dim},
]
dec = _default_decoder(latent_dim, [], input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="classic",
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class PreprocessedAutoencoderConfig(AutoencoderConfig):
"""Classic MLP AE with learnable preprocessing/inverse.
Example:
cfg = PreprocessedAutoencoderConfig(input_dim=64, preprocessing_type="neural_scaler")
"""
def __init__(self, input_dim: int = 64, latent_dim: int = 32, preprocessing_type: str = "neural_scaler", hidden: List[int] = (128, 64), activation: str = "relu", dropout: float = 0.0, use_batch_norm: bool = True, **kwargs):
norm = "batch" if use_batch_norm else "none"
enc = _linear_stack(input_dim, list(hidden), activation, norm, dropout)
dec = _default_decoder(latent_dim, list(reversed(list(hidden))), input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="classic",
use_learnable_preprocessing=True,
preprocessing_type=preprocessing_type,
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class BetaVariationalAutoencoderConfig(AutoencoderConfig):
"""Beta-VAE (MLP). Like VAE but with beta > 1 controlling KL weight.
Example:
cfg = BetaVariationalAutoencoderConfig(input_dim=784, latent_dim=32, beta=4.0)
"""
def __init__(self, input_dim: int = 784, latent_dim: int = 32, hidden: List[int] = (512, 256, 128), activation: str = "relu", dropout: float = 0.1, use_batch_norm: bool = True, beta: float = 4.0, **kwargs):
hidden = list(hidden)
norm = "batch" if use_batch_norm else "none"
enc = _linear_stack(input_dim, hidden, activation, norm, dropout)
dec = _default_decoder(latent_dim, list(reversed(hidden)), input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="beta_vae",
beta=beta,
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class DenoisingAutoencoderConfig(AutoencoderConfig):
"""Denoising AE: adds noise during training (handled by training loop/model if supported).
Example:
cfg = DenoisingAutoencoderConfig(input_dim=128, latent_dim=32, noise_factor=0.2)
"""
def __init__(self, input_dim: int = 128, latent_dim: int = 32, hidden: List[int] = (128, 64), activation: str = "relu", dropout: float = 0.0, use_batch_norm: bool = True, noise_factor: float = 0.2, **kwargs):
hidden = list(hidden)
norm = "batch" if use_batch_norm else "none"
enc = _linear_stack(input_dim, hidden, activation, norm, dropout)
dec = _default_decoder(latent_dim, list(reversed(hidden)), input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="denoising",
noise_factor=noise_factor,
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class SparseAutoencoderConfig(AutoencoderConfig):
"""Sparse AE (typical L1 activation penalty applied in training loop).
Example:
cfg = SparseAutoencoderConfig(input_dim=256, latent_dim=64)
"""
def __init__(self, input_dim: int = 256, latent_dim: int = 64, hidden: List[int] = (128, 64), activation: str = "relu", dropout: float = 0.0, use_batch_norm: bool = True, **kwargs):
hidden = list(hidden)
norm = "batch" if use_batch_norm else "none"
enc = _linear_stack(input_dim, hidden, activation, norm, dropout)
dec = _default_decoder(latent_dim, list(reversed(hidden)), input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="sparse",
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
class ContractiveAutoencoderConfig(AutoencoderConfig):
"""Contractive AE (requires Jacobian penalty in training loop).
Example:
cfg = ContractiveAutoencoderConfig(input_dim=64, latent_dim=16)
"""
def __init__(self, input_dim: int = 64, latent_dim: int = 16, hidden: List[int] = (64, 32), activation: str = "relu", dropout: float = 0.0, use_batch_norm: bool = True, **kwargs):
hidden = list(hidden)
norm = "batch" if use_batch_norm else "none"
enc = _linear_stack(input_dim, hidden, activation, norm, dropout)
dec = _default_decoder(latent_dim, list(reversed(hidden)), input_dim, activation, norm, dropout)
super().__init__(
input_dim=input_dim,
latent_dim=latent_dim,
activation=activation,
dropout_rate=dropout,
use_batch_norm=use_batch_norm,
autoencoder_type="contractive",
encoder_blocks=enc,
decoder_blocks=dec,
**kwargs,
)
__all__ = [
"ClassicAutoencoderConfig",
"VariationalAutoencoderConfig",
"TransformerAutoencoderConfig",
"RecurrentAutoencoderConfig",
"ConvolutionalAutoencoderConfig",
"ConvAttentionAutoencoderConfig",
"LinearRecurrentAutoencoderConfig",
"PreprocessedAutoencoderConfig",
"BetaVariationalAutoencoderConfig",
"DenoisingAutoencoderConfig",
"SparseAutoencoderConfig",
"ContractiveAutoencoderConfig",
]
|