def fit_autoencoder(image_size=(28, 28),
n_image_channels=1,
datasets='../data/mnist.pkl.gz',
outpath='../output/mnist_autoencoder.params',
n_visible=784,
n_hidden=500,
learning_rate=0.01,
corruption_level=0.0,
n_epochs=1000,
batch_size=20,
patience=10000,
patience_increase=2,
improvement_threshold=0.995):
index = T.lscalar()
x = T.dmatrix(name='input')
encoder = AutoEncoder(np_rng=rng.RandomState(SEED),
input=x,
th_rng=None,
n_visible=n_visible,
n_hidden=n_hidden,
corruption_level=corruption_level)
learner = UnsupervisedMSGD(index, x, batch_size, learning_rate,
load_data(datasets), outpath, encoder,
encoder.cost)
best_validation_error, best_iter, epoch, elapsed_time = learner.fit(
n_epochs=n_epochs,
patience=patience,
patience_increase=patience_increase,
improvement_threshold=improvement_threshold)
display_results(best_validation_error, elapsed_time, epoch)
return learner
def fit_autoencoder(image_size=(28, 28), n_image_channels=1,
datasets='../data/mnist.pkl.gz', outpath='../output/mnist_autoencoder.params',
n_visible=784, n_hidden=500,
learning_rate=0.01, corruption_level=0.0,
n_epochs=1000, batch_size=20, patience=10000,
patience_increase=2, improvement_threshold=0.995):
index = T.lscalar()
x = T.dmatrix(name='input')
encoder = AutoEncoder(
np_rng=rng.RandomState(SEED),
input=x,
th_rng=None,
n_visible=n_visible,
n_hidden=n_hidden,
corruption_level=corruption_level
)
learner = UnsupervisedMSGD(
index,
x,
batch_size,
learning_rate,
load_data(datasets),
outpath,
encoder,
encoder.cost
)
best_validation_error, best_iter, epoch, elapsed_time = learner.fit(
n_epochs=n_epochs,
patience=patience,
patience_increase=patience_increase,
improvement_threshold=improvement_threshold
)
display_results(best_validation_error, elapsed_time, epoch)
return learner
def fit_stacked_autoencoder(image_size=(28, 28), n_out=10,
datasets='../data/mnist.pkl.gz', outpath='../output/mnist_autoencoder.params',
hidden_layer_sizes=[500, 500, 500], corruption_levels=[0.1, 0.2, 0.3],
learning_rate_encoder=0.001, learning_rate_full=0.1,
n_epochs_encoder=15, n_epochs_full=1000,
batch_size_encoder=1, batch_size_full=20,
patience_encoder=5000, patience_full=5000,
patience_increase=2, improvement_threshold=0.995):
n_inputs = reduce(np.multiply, image_size)
index = T.lscalar(name='input')
x = T.matrix(name='x')
y = T.ivector(name='y')
datasets = load_data(datasets)
stacked_encoder = StackedAutoEncoder(
x=x,
y=y,
np_rng=rng,
th_rng=None,
n_inputs=n_inputs,
hidden_layer_sizes=hidden_layer_sizes,
corruption_levels=corruption_levels,
n_out=n_out
)
cost = stacked_encoder.cost(y)
# pretrain
for i, encoder in enumerate(stacked_encoder.encoder_layers):
print("Pre-training encoder layer %i" % i)
learner = UnsupervisedMSGD(
index,
x,
batch_size_encoder,
learning_rate_encoder,
datasets,
None,
encoder,
encoder.cost
)
best_validation_error, best_iter, epoch, elapsed_time = learner.fit(
n_epochs=n_epochs_encoder,
patience=patience_encoder,
patience_increase=patience_increase,
improvement_threshold=improvement_threshold
)
print("resuts for pre-training encoder %i" % i)
display_results(best_validation_error, elapsed_time, epoch)
print("Fitting full model")
learner = SupervisedMSGD(
index,
x,
y,
batch_size_full,
learning_rate_full,
datasets,
outpath,
stacked_encoder,
cost
)
best_validation_error, best_iter, epoch, elapsed_time = learner.fit(
n_epochs=n_epochs_full,
patience=patience_full,
patience_increase=patience_increase,
improvement_threshold=improvement_threshold
)
display_results(best_validation_error, elapsed_time, epoch)