import pydeep.base.numpyextension as numxext
import pydeep.misc.io as io
import pydeep.preprocessing as pre
import pydeep.misc.visualization as vis
# Model imports: RBM estimator, model and trainer module
import pydeep.rbm.estimator as estimator
import pydeep.rbm.model as model
import pydeep.rbm.trainer as trainer
# Set random seed (optional)
# (optional, if stochastic processes are involved we get the same results)
numx.random.seed(42)
# Load data (download is not existing)
data = io.load_natural_image_patches('NaturalImage.mat')
# Remove the mean of ech image patch separately (also works without)
data = pre.remove_rows_means(data)
# Set input/output dimensions
v1 = 14
v2 = 14
h1 = 14
h2 = 14
# Whiten data using ZCA
zca = pre.ZCA(v1 * v2)
zca.train(data)
data = zca.project(data)
import numpy as numx
import pydeep.misc.io as io
import pydeep.misc.visualization as vis
import pydeep.preprocessing as pre
# Import cost functions, activation function, Autencoder and trainer module
import pydeep.base.activationfunction as act
import pydeep.base.costfunction as cost
import pydeep.ae.model as aeModel
import pydeep.ae.trainer as aeTrainer
# Set random seed
numx.random.seed(42)
# Load data (download is not existing)
data = io.load_natural_image_patches('../../../data/NaturalImage.mat')
# Remove mean individually
data = pre.remove_rows_means(data)
# Shuffle data
data = numx.random.permutation(data)
# Specify input and hidden dimensions
h1 = 20
h2 = 20
v1 = 14
v2 = 14
# Whiten data using ZCA or change it to STANDARIZER for unwhitened results
zca = pre.ZCA(v1 * v2)
