log.info("Creating RBM!")
# grab the MNIST dataset
mnist = MNIST(concat_train_valid=False)
# create the RBM
rng = numpy.random.RandomState(1234)
mrg = theano.tensor.shared_randomstreams.RandomStreams(rng.randint(2**30))
config_args = {
'inputs': (28*28, theano.tensor.matrix('x')),
'hiddens': 500,
'k': 15,
'weights_init': 'uniform',
'weights_interval': 4*numpy.sqrt(6./28*28+500),
'mrg': mrg
}
rbm = RBM(**config_args)
# rbm.load_params('outputs/rbm/trained_epoch_15.pkl')
optimizer = Optimizer(learning_rate=0.1, model=rbm, dataset=mnist, batch_size=20, epochs=15)
# perform training!
optimizer.train()
# test it on some images!
test_data = mnist.test_inputs[:25]
# use the run function!
preds = rbm.run(test_data)
# Construct image from the test matrix
image = Image.fromarray(
tile_raster_images(
log.info("Creating RBM!")
# grab the MNIST dataset
mnist = MNIST(concat_train_valid=False)
# create the RBM
rng = numpy.random.RandomState(1234)
mrg = theano.tensor.shared_randomstreams.RandomStreams(rng.randint(2**30))
config_args = {
'inputs': (28*28, theano.tensor.matrix('x')),
'hiddens': 500,
'k': 15,
'weights_init': 'uniform',
'weights_interval': 4*numpy.sqrt(6./28*28+500),
'mrg': mrg
}
rbm = RBM(**config_args)
# rbm.load_params('outputs/rbm/trained_epoch_15.pkl')
optimizer = Optimizer(learning_rate=0.1, model=rbm, dataset=mnist, batch_size=20, epochs=15)
# perform training!
optimizer.train()
# test it on some images!
test_data = mnist.test_inputs[:25]
# use the run function!
preds = rbm.run(test_data)
if has_pil:
# Construct image from the test matrix
image = Image.fromarray(
log.info("Creating RBM!")
# grab the MNIST dataset
mnist = MNIST(concat_train_valid=False)
# create the RBM
rng = numpy.random.RandomState(1234)
mrg = theano.tensor.shared_randomstreams.RandomStreams(rng.randint(2**30))
config_args = {
'input_size': 28 * 28,
'hidden_size': 500,
'k': 15,
'weights_init': 'uniform',
'weights_interval': 4 * numpy.sqrt(6. / 28 * 28 + 500),
'mrg': mrg
}
rbm = RBM(**config_args)
# rbm.load_params('rbm_trained.pkl')
optimizer = Optimizer(learning_rate=0.1,
model=rbm,
dataset=mnist,
batch_size=20,
epochs=15)
ll = Monitor('pseudo-log', rbm.get_monitors()['pseudo-log'])
# perform training!
optimizer.train(monitor_channels=ll)
# test it on some images!
test_data = mnist.test_inputs[:25]
# use the run function!
log.info("Creating RBM!")
# grab the MNIST dataset
mnist = MNIST(concat_train_valid=False)
# create the RBM
rng = numpy.random.RandomState(1234)
mrg = theano.tensor.shared_randomstreams.RandomStreams(rng.randint(2 ** 30))
config_args = {
"input_size": 28 * 28,
"hidden_size": 500,
"k": 15,
"weights_init": "uniform",
"weights_interval": 4 * numpy.sqrt(6.0 / 28 * 28 + 500),
"mrg": mrg,
}
rbm = RBM(**config_args)
# rbm.load_params('rbm_trained.pkl')
optimizer = Optimizer(learning_rate=0.1, model=rbm, dataset=mnist, batch_size=20, epochs=15)
ll = Monitor("pseudo-log", rbm.get_monitors()["pseudo-log"])
# perform training!
optimizer.train(monitor_channels=ll)
# test it on some images!
test_data = mnist.test_inputs[:25]
# use the run function!
preds = rbm.run(test_data)
# Construct image from the test matrix
image = Image.fromarray(tile_raster_images(X=test_data, img_shape=(28, 28), tile_shape=(5, 5), tile_spacing=(1, 1)))