def main():
dataset_file = 'mnist.npz'
if not isfile(dataset_file):
downloadMnist(dataset_file)
data = dict(np.load(dataset_file))
data['x_tr'] = data['x_tr'] * 2.0 - 1.0
data['x_va'] = data['x_va'] * 2.0 - 1.0
data['x_te'] = data['x_te'] * 2.0 - 1.0
data['t_tr'] = data['t_tr'].astype(np.int32)
data['t_va'] = data['t_va'].astype(np.int32)
data['t_te'] = data['t_te'].astype(np.int32)
rng = np.random.RandomState()
srng = RandomStreamsGPU(rng.randint(1, 2147462579, size=(6,)))
# Setup data loaders
train_generator = DefaultDataLoader(data['x_tr'], data['t_tr'], 100, rng=rng)
validation_generator = DefaultDataLoader(data['x_va'], data['t_va'], 100)
test_generator = DefaultDataLoader(data['x_te'], data['t_te'], 100)
# Load real-valued model parameters for initialization
init_model_file = 'mnist_pi_model_ternary_tanh.npz'
if isfile(init_model_file):
initial_parameters = dict(np.load(init_model_file))
print 'Loading initial parameters from \'%s\'' % (init_model_file)
print 'Parameters:', [e for e in initial_parameters]
else:
raise Exception('Cannot find initial model \'%s\'' % (init_model_file))
# Create model
global parameters
layer, parameters = getMnistPIModel(initial_parameters, rng, srng)
# Do optimization
print layer.getMessage()
cbErrVaDecreased = lambda : cbValidationErrorDecreased()
global p_vals
optimizeNetwork(layer,
loader_tr=train_generator,
loader_va=validation_generator,
loader_te=test_generator,
optimization_algorithm='adam',
step_size=1e-3,
step_size_discrete=1e-2,
step_size_scale_fn={'type' : 'plateau',
'monitor' : 'ce_va',
'cooldown' : 50,
'patience' : 10,
'factor' : 0.5},
n_epochs=500,
do_bn_updates_after_epoch=True,
callback_validation_error_decreased=[(cbErrVaDecreased, [])])
# Store model parameters. The model parameters of the best model according to the validation error are now in
# p_vals.
model_file = 'mnist_pi_model_ternary_sign_from_tanh.npz'
print 'Optimization finished. Storing model parameters to ''%s''' % model_file
np.savez_compressed(model_file, **p_vals)
def main():
dataset_file = 'mnist.npz'
if not isfile(dataset_file):
downloadMnist(dataset_file)
data = dict(np.load(dataset_file))
data['x_tr'] = data['x_tr'] * 2.0 - 1.0
data['x_va'] = data['x_va'] * 2.0 - 1.0
data['x_te'] = data['x_te'] * 2.0 - 1.0
data['t_tr'] = data['t_tr'].astype(np.int32)
data['t_va'] = data['t_va'].astype(np.int32)
data['t_te'] = data['t_te'].astype(np.int32)
rng = np.random.RandomState()
srng = RandomStreamsGPU(rng.randint(1, 2147462579, size=(6, )))
# Setup data loaders
train_generator = DefaultDataLoader(data['x_tr'],
data['t_tr'],
100,
rng=rng)
validation_generator = DefaultDataLoader(data['x_va'], data['t_va'], 100)
test_generator = DefaultDataLoader(data['x_te'], data['t_te'], 100)
# Create model
global parameters
layer, parameters = getMnistPIModel(rng, srng)
# Do optimization
print layer.getMessage()
cbErrVaDecreased = lambda: cbValidationErrorDecreased()
global p_vals
optimizeNetwork(layer,
loader_tr=train_generator,
loader_va=validation_generator,
loader_te=test_generator,
optimization_algorithm='adam',
step_size=1e-3,
step_size_scale_fn={
'type': 'plateau',
'monitor': 'ce_va',
'cooldown': 150,
'patience': 25,
'factor': 0.5
},
n_epochs=1000,
callback_validation_error_decreased=[(cbErrVaDecreased, [])
])
# Store model parameters. The model parameters of the best model according to the validation error are now in
# p_vals.
model_file = 'mnist_pi_model_real.npz'
print 'Optimization finished. Storing model parameters to ' '%s' '' % model_file
np.savez_compressed(model_file, **p_vals)
def main():
dataset_file = 'cifar100.npz'
if not isfile(dataset_file):
downloadCifar100(dataset_file)
data = dict(np.load(dataset_file))
data['x_tr'] = ((data['x_tr'] / 255.0 * 2.0) - 1.0).astype(
np.float32).reshape(-1, 3, 32, 32)
data['x_va'] = ((data['x_va'] / 255.0 * 2.0) - 1.0).astype(
np.float32).reshape(-1, 3, 32, 32)
data['x_te'] = ((data['x_te'] / 255.0 * 2.0) - 1.0).astype(
np.float32).reshape(-1, 3, 32, 32)
data['t_tr'] = data['t_tr'].astype(np.int32)
data['t_va'] = data['t_va'].astype(np.int32)
data['t_te'] = data['t_te'].astype(np.int32)
rng = np.random.RandomState()
srng = RandomStreamsGPU(rng.randint(1, 2147462579, size=(6, )))
# Setup data loaders
train_generator = Cifar10FlipShiftDataLoader(data['x_tr'],
data['t_tr'],
100,
flip_axis=1,
max_shift=4,
requires_train=True,
rng=rng)
validation_generator = DefaultDataLoader(data['x_va'], data['t_va'], 100)
test_generator = DefaultDataLoader(data['x_te'], data['t_te'], 100)
# Create model
global parameters
layer, parameters = getCifar100Model(rng, srng)
# Do optimization
print layer.getMessage()
cbErrVaDecreased = lambda: cbValidationErrorDecreased()
global p_vals
optimizeNetwork(layer,
loader_tr=train_generator,
loader_va=validation_generator,
loader_te=test_generator,
optimization_algorithm='adam',
step_size=3e-4,
step_size_scale_fn={
'type': 'plateau',
'monitor': 'ce_va',
'cooldown': 50,
'patience': 10,
'factor': 0.5
},
n_epochs=500,
callback_validation_error_decreased=[(cbErrVaDecreased, [])
])
# Store model parameters. The model parameters of the best model according to the validation error are now in
# p_vals.
model_file = 'cifar100_model_real.npz'
print 'Optimization finished. Storing model parameters to ' '%s' '' % model_file
np.savez_compressed(model_file, **p_vals)
