I'm trying to execute a Bayesian Neural Network that I found on the paper "Uncertainty on Deep Learning", Yarin Gal. I found this code on GitHub:
import math
from scipy.misc import logsumexp
import numpy as np
from keras.regularizers import l2
from keras import Input
from keras.layers import Dropout
from keras.layers import Dense
from keras import Model
import time
class net:
def __init__(self, X_train, y_train, n_hidden, n_epochs = 40,
normalize = False, tau = 1.0, dropout = 0.05):
"""
Constructor for the class implementing a Bayesian neural network
trained with the probabilistic back propagation method.
@param X_train Matrix with the features for the training data.
@param y_train Vector with the target variables for the
training data.
@param n_hidden Vector with the number of neurons for each
hidden layer.
@param n_epochs Number of epochs for which to train the
network. The recommended value 40 should be
enough.
@param normalize Whether to normalize the input features. This
is recommended unless the input vector is for
example formed by binary features (a
fingerprint). In that case we do not recommend
to normalize the features.
@param tau Tau value used for regularization
@param dropout Dropout rate for all the dropout layers in the
network.
"""
# We normalize the training data to have zero mean and unit standard
# deviation in the training set if necessary
if normalize:
self.std_X_train = np.std(X_train, 0)
self.std_X_train[ self.std_X_train == 0 ] = 1
self.mean_X_train = np.mean(X_train, 0)
else:
self.std_X_train = np.ones(X_train.shape[ 1 ])
self.mean_X_train = np.zeros(X_train.shape[ 1 ])
X_train = (X_train - np.full(X_train.shape, self.mean_X_train)) / \
np.full(X_train.shape, self.std_X_train)
self.mean_y_train = np.mean(y_train)
self.std_y_train = np.std(y_train)
y_train_normalized = (y_train - self.mean_y_train) / self.std_y_train
y_train_normalized = np.array(y_train_normalized, ndmin = 2).T
# We construct the network
N = X_train.shape[0]
batch_size = 128
lengthscale = 1e-2
reg = lengthscale**2 * (1 - dropout) / (2. * N * tau)
inputs = Input(shape=(X_train.shape[1],))
inter = Dropout(dropout)(inputs, training=True)
inter = Dense(n_hidden[0], activation='relu', W_regularizer=l2(reg))(inter)
for i in range(len(n_hidden) - 1):
inter = Dropout(dropout)(inter, training=True)
inter = Dense(n_hidden[i+1], activation='relu', W_regularizer=l2(reg))(inter)
inter = Dropout(dropout)(inter, training=True)
outputs = Dense(y_train_normalized.shape[1], W_regularizer=l2(reg))(inter)
model = Model(inputs, outputs)
model.compile(loss='mean_squared_error', optimizer='adam')
# We iterate the learning process
start_time = time.time()
model.fit(X_train, y_train_normalized, batch_size=batch_size, nb_epoch=n_epochs, verbose=0)
self.model = model
self.tau = tau
self.running_time = time.time() - start_time
# We are done!
def predict(self, X_test, y_test):
"""
Function for making predictions with the Bayesian neural network.
@param X_test The matrix of features for the test data
@return m The predictive mean for the test target variables.
@return v The predictive variance for the test target
variables.
@return v_noise The estimated variance for the additive noise.
"""
X_test = np.array(X_test, ndmin = 2)
y_test = np.array(y_test, ndmin = 2).T
# We normalize the test set
X_test = (X_test - np.full(X_test.shape, self.mean_X_train)) / \
np.full(X_test.shape, self.std_X_train)
# We compute the predictive mean and variance for the target variables
# of the test data
model = self.model
standard_pred = model.predict(X_test, batch_size=500, verbose=1)
standard_pred = standard_pred * self.std_y_train + self.mean_y_train
rmse_standard_pred = np.mean((y_test.squeeze() - standard_pred.squeeze())**2.)**0.5
T = 10000
Yt_hat = np.array([model.predict(X_test, batch_size=500, verbose=0) for _ in range(T)])
Yt_hat = Yt_hat * self.std_y_train + self.mean_y_train
MC_pred = np.mean(Yt_hat, 0)
rmse = np.mean((y_test.squeeze() - MC_pred.squeeze())**2.)**0.5
# We compute the test log-likelihood
ll = (logsumexp(-0.5 * self.tau * (y_test[None] - Yt_hat)**2., 0) - np.log(T)
- 0.5*np.log(2*np.pi) + 0.5*np.log(self.tau))
test_ll = np.mean(ll)
# We are done!
return rmse_standard_pred, rmse, test_ll
I'm new at programming, so I have to study Classes on Python to understand the code. But my answer goes when I try to execute the code, but it ask a "vector with the numbers of neurons for each hidden layer", and I don't know how to create this vector, and which does it mean for the code. I've tried to create different vectors, like
vector = np.array([1, 2, 3])
but sincerely I don't know the correct answer. The only I have is the feature data and the target data. I hope you can help me.
That syntax is correct vector = np.array([1, 2, 3])
. That is the way to define a vector in python's numpy.
A neural network can have any number o hidden (internal) layers. And each layer will have a certain number of neurons.
So in this code, a vector=np.array([100, 150, 100])
, means that the network should have 3 hidden layers (because the vector has 3 values), and the hidden layers should have, from input to output 100, 150, 100 neurons respectively.