def test_cgan_fashion_mnist(show_figure=False, block_figure_on_end=False):
print("========== Test CGAN on Fashion-MNIST data ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_fashion_mnist()
x_train = x_train.astype(np.float32).reshape([-1, 28, 28, 1]) / 0.5 - 1.
x_test = x_test.astype(np.float32).reshape([-1, 28, 28, 1]) / 0.5 - 1.
loss_display = Display(layout=(1, 1),
dpi='auto',
show=show_figure,
block_on_end=block_figure_on_end,
monitor=[
{
'metrics': ['d_loss', 'g_loss'],
'type':
'line',
'labels':
["discriminator loss", "generator loss"],
'title':
"CGAN: Losses",
'xlabel':
"epoch",
'ylabel':
"loss",
},
])
sample_display = Display(layout=(1, 1),
dpi='auto',
figsize=(10, 10),
freq=1,
show=show_figure,
block_on_end=block_figure_on_end,
monitor=[
{
'metrics': ['x_samples'],
'title': "CGAN: Generated data",
'type': 'img',
'num_samples': 100,
'tile_shape': (10, 10),
},
])
model = CGAN(
model_name="CGAN_Fashion-MNIST",
num_z=10, # set to 100 for a full run
z_prior=Uniform1D(low=-1.0, high=1.0),
img_size=(28, 28, 1),
batch_size=64, # set to 64 for a full run
num_conv_layers=3, # set to 3 for a full run
num_gen_feature_maps=2, # set to 64 for a full run
num_dis_feature_maps=2, # set to 64 for a full run
metrics=['d_loss', 'g_loss'],
callbacks=[loss_display, sample_display],
num_epochs=1, # set to 100 for a full run
random_state=random_seed(),
verbose=1)
model.fit(x_train, y_train)
def test_wgan_gp_fashion_mnist(show_figure=False, block_figure_on_end=False):
print("========== Test WGAN-GP on Fashion-MNIST data ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_fashion_mnist()
x_train = x_train.astype(np.float32).reshape([-1, 28, 28, 1]) / 0.5 - 1.
x_test = x_test.astype(np.float32).reshape([-1, 28, 28, 1]) / 0.5 - 1.
root_dir = os.path.join(model_dir(), "male/WGAN-GP/FashionMNIST")
loss_display = Display(layout=(1, 1),
dpi='auto',
show=show_figure,
block_on_end=block_figure_on_end,
filepath=[os.path.join(root_dir, "loss/loss_{epoch:04d}.png"),
os.path.join(root_dir, "loss/loss_{epoch:04d}.pdf")],
monitor=[{'metrics': ['d_loss', 'g_loss'],
'type': 'line',
'labels': ["discriminator loss", "generator loss"],
'title': "Losses",
'xlabel': "epoch",
'ylabel': "loss",
},
])
sample_display = Display(layout=(1, 1),
dpi='auto',
figsize=(10, 10),
freq=1,
show=show_figure,
block_on_end=block_figure_on_end,
monitor=[{'metrics': ['x_samples'],
'title': "Generated data",
'type': 'img',
'num_samples': 100,
'tile_shape': (10, 10),
},
])
model = WGAN_GP(model_name="WGAN_GP_FashionMNIST",
num_z=10, # set to 100 for a full run
z_prior=Uniform1D(low=-1.0, high=1.0),
img_size=(28, 28, 1),
batch_size=16, # set to 64 for a full run
num_conv_layers=3, # set to 3 for a full run
num_gen_feature_maps=4, # set to 64 for a full run
num_dis_feature_maps=4, # set to 64 for a full run
metrics=['d_loss', 'g_loss'],
callbacks=[loss_display, sample_display],
num_epochs=4, # set to 100 for a full run
random_state=random_seed(),
log_path=os.path.join(root_dir, "logs"),
verbose=1)
model.fit(x_train)
model = WGAN_GP(model_name="WGAN_GP_FashionMNIST",
num_z=10, # set to 100 for a full run
z_prior=Gaussian1D(mu=0.0, sigma=1.0),
img_size=(28, 28, 1),
batch_size=32, # set to 64 for a full run
num_conv_layers=3, # set to 3 for a full run
num_gen_feature_maps=4, # set to 64 for a full run
num_dis_feature_maps=4, # set to 64 for a full run
metrics=['d_loss', 'g_loss'],
callbacks=[loss_display, sample_display],
num_epochs=4, # set to 100 for a full run
random_state=random_seed(),
log_path=os.path.join(root_dir, "logs"),
verbose=1)
model.fit(x_train)
def test_fashion_mnist(show=False, block_figure_on_end=False):
print("========== Test Fashion-MNIST dataset using GLM ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_fashion_mnist()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
x = np.vstack([x_train, x_test])
y = np.concatenate([y_train, y_test])
early_stopping = EarlyStopping(monitor='val_err', patience=2, verbose=1)
filepath = os.path.join(
model_dir(),
"male/datasets/fashion_mnist_{epoch:04d}_{val_err:.6f}.pkl")
checkpoint = ModelCheckpoint(filepath,
mode='min',
monitor='val_err',
verbose=0,
save_best_only=True)
loss_display = Display(title="Learning curves",
dpi='auto',
layout=(3, 1),
freq=1,
show=show,
block_on_end=block_figure_on_end,
monitor=[
{
'metrics': ['loss', 'val_loss'],
'type': 'line',
'labels':
["training loss", "validation loss"],
'title': "Learning losses",
'xlabel': "epoch",
'ylabel': "loss",
},
{
'metrics': ['err', 'val_err'],
'type': 'line',
'title': "Learning errors",
'xlabel': "epoch",
'ylabel': "error",
},
{
'metrics': ['err'],
'type': 'line',
'labels': ["training error"],
'title': "Learning errors",
'xlabel': "epoch",
'ylabel': "error",
},
])
weight_display = Display(title="Filters",
dpi='auto',
layout=(1, 1),
figsize=(3, 24),
freq=1,
show=show,
block_on_end=block_figure_on_end,
monitor=[
{
'metrics': ['weights'],
'title': "Learned weights",
'type': 'img',
'disp_dim': (28, 28),
'tile_shape': (10, 1),
},
])
clf = GLM(
model_name="GLM_softmax_cv",
link='softmax',
loss='softmax',
optimizer='sgd',
num_epochs=4,
batch_size=10,
task='classification',
metrics=['loss', 'err'],
callbacks=[early_stopping, checkpoint, loss_display, weight_display],
cv=[-1] * x_train.shape[0] + [0] * x_test.shape[0],
random_state=random_seed(),
verbose=1)
clf.fit(x, y)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
def test_gan_fashion_mnist(show_figure=False, block_figure_on_end=False):
print("========== Test GAN on Fashion-MNIST data ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_fashion_mnist()
x_train = x_train.astype(np.float32)
x_test = x_test.astype(np.float32)
loss_display = Display(layout=(1, 1),
dpi='auto',
show=show_figure,
block_on_end=block_figure_on_end,
monitor=[
{
'metrics': ['d_loss', 'g_loss'],
'type':
'line',
'labels':
["discriminator loss", "generator loss"],
'title':
"Losses",
'xlabel':
"epoch",
'ylabel':
"loss",
},
])
sample_display = Display(layout=(1, 1),
dpi='auto',
figsize=(10, 10),
freq=1,
show=show_figure,
block_on_end=block_figure_on_end,
monitor=[
{
'metrics': ['x_samples'],
'title': "Generated data",
'type': 'img',
'num_samples': 100,
'disp_dim': (28, 28),
'tile_shape': (10, 10),
},
])
# <editor-fold desc="Working example">
# model = GAN(num_x=784,
# num_discriminator_hiddens=(128,),
# discriminator_batchnorm=False,
# discriminator_act_funcs=('lrelu',),
# discriminator_learning_rate=0.001,
# num_z=100,
# generator_distribution=Uniform(low=(-1.0,) * 100, high=(1.0,) * 100),
# generator_batchnorm=False,
# num_generator_hiddens=(128,),
# generator_act_funcs=('lrelu',),
# generator_out_func='sigmoid',
# generator_learning_rate=0.001,
# batch_size=32,
# metrics=['d_loss', 'g_loss'],
# callbacks=[loss_display, sample_display],
# num_epochs=100,
# random_state=random_seed(),
# verbose=1)
# </editor-fold>
# <editor-fold desc="Testing example">
NUM_Z = 10 # set to 100 for a full run
model = GAN(
num_x=784,
num_discriminator_hiddens=(16, ), # set to 128 for a full run
discriminator_batchnorm=False,
discriminator_act_funcs=('lrelu', ),
discriminator_dropouts=(0.99, ),
discriminator_learning_rate=0.001,
num_z=NUM_Z,
generator_distribution=Uniform(low=(-1.0, ) * NUM_Z,
high=(1.0, ) * NUM_Z),
generator_batchnorm=False,
num_generator_hiddens=(16, 16), # set to (128, 128) for a full run
generator_act_funcs=('lrelu', 'lrelu'),
generator_out_func='sigmoid',
generator_learning_rate=0.001,
batch_size=32,
metrics=['d_loss', 'g_loss'],
callbacks=[loss_display, sample_display],
num_epochs=4, # set to 100 for a full run
random_state=random_seed(),
verbose=1)
# </editor-fold>
model.fit(x_train)