import time
from typing import Optional, Tuple
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as opt
from torch.utils.data import DataLoader
from tqdm import tqdm
import learnergy.utils.constants as c
import learnergy.utils.exception as e
from learnergy.core import Model
from learnergy.utils import logging
logger = logging.get_logger(__name__)
class RBM(Model):
"""An RBM class provides the basic implementation for Bernoulli-Bernoulli Restricted Boltzmann Machines.
References:
G. Hinton. A practical guide to training restricted Boltzmann machines.
Neural networks: Tricks of the trade (2012).
"""
def __init__(
self,
n_visible: Optional[int] = 128,
n_hidden: Optional[int] = 128,
steps: Optional[int] = 1,
def test_get_logger():
logger = logging.get_logger(__name__)
assert logger.name == "test_logging"
assert logger.hasHandlers() is True
"""Discriminative Bernoulli-Bernoulli Restricted Boltzmann Machine.
"""
import time
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.data import DataLoader
from tqdm import tqdm
import learnergy.utils.exception as e
import learnergy.utils.logging as l
from learnergy.models.bernoulli import RBM
logger = l.get_logger(__name__)
class DiscriminativeRBM(RBM):
"""A DiscriminativeRBM class provides the basic implementation for
Discriminative Bernoulli-Bernoulli Restricted Boltzmann Machines.
References:
H. Larochelle and Y. Bengio. Classification using discriminative restricted Boltzmann machines.
Proceedings of the 25th international conference on Machine learning (2008).
"""
def __init__(self,
n_visible=128,
n_hidden=128,
n_classes=1,
def test_get_logger():
logger = logging.get_logger(__name__)
assert logger.name == 'test_logging'
assert logger.hasHandlers() == True
