def PNtrain(dataset: str, batch_size=30500, lr=1e-3):
if dataset == 'MNIST':
(x_train, y_train), (x_test, y_test) = MNIST()
model = MLP(n_layers=6, activation='relu', use_softmax=True)
optimizer = tf.keras.optimizers.Adam(lr=lr)
elif dataset == 'epsilon':
(x_train, y_train), (x_test, y_test) = Epsilon()
model = MLP(n_layers=6, activation='softsign', use_softmax=True)
optimizer = tf.keras.optimizers.Adam(lr=lr)
elif dataset == '20News':
(x_train, y_train), (x_test, y_test) = News20()
model = MLP(n_layers=5, activation='softsign', use_softmax=True)
optimizer = tf.keras.optimizers.Adagrad(lr=lr)
elif dataset == 'CIFAR-10':
(x_train, y_train), (x_test, y_test) = Cifar10()
model = CNN(use_softmax=True)
optimizer = tf.keras.optimizers.Adam(lr=lr)
else:
raise ValueError('Incorrect argument!')
pi_p = np.count_nonzero(y_train) / y_train.size
pi_n = 1 - pi_p
n_p = 1000
n_n = int(np.round((pi_n / 2 / pi_p)**2 * n_p))
p_index = np.random.choice(y_train.sum(), n_p)
n_index = np.random.choice(np.logical_not(y_train).sum(), n_n)
train_data_x = np.concatenate(
(x_train[y_train][p_index], x_train[np.logical_not(y_train)][n_index]))
train_data_y = np.concatenate((np.ones(n_p), np.zeros(n_n)))
train_data_x, x_test = train_data_x / 255., x_test / 255.
model.compile(optimizer=optimizer,
loss='sparse_categorical_crossentropy',
metrics=['acc'])
if os.path.isdir('logs/' + dataset + '-PN'):
print('Error: log dir exist')
exit(1)
tensorboard = tf.keras.callbacks.TensorBoard(
log_dir="logs/{}/train".format(dataset + '-PN'))
summary_writer = tf.summary.FileWriter("logs/{}/test".format(dataset +
'-PN'))
for i in range(10000):
model.fit(train_data_x,
train_data_y,
batch_size=batch_size,
epochs=i + 1,
shuffle=True,
callbacks=[tensorboard],
initial_epoch=i)
lossval, acc = model.evaluate(x_test, y_test, batch_size=batch_size)
summary = tf.Summary()
summary.value.add(tag='test-loss', simple_value=lossval)
summary.value.add(tag='test-accuracy', simple_value=acc)
summary.value.add(tag='test-error', simple_value=1 - acc)
summary_writer.add_summary(summary, i)
summary_writer.flush()
def PUtrain(dataset: str, func_loss, batch_size=30500, lr=1e-3, pretrain='no'):
if dataset == 'MNIST':
(x_train, y_train), (x_test, y_test) = MNIST()
model = MLP(n_layers=6, activation='relu', use_softmax=False)
optimizer = tf.keras.optimizers.Adam(lr=lr)
elif dataset == 'epsilon':
(x_train, y_train), (x_test, y_test) = Epsilon()
model = MLP(n_layers=6, activation='softsign', use_softmax=False)
optimizer = tf.keras.optimizers.Adam(lr=lr)
elif dataset == '20News':
(x_train, y_train), (x_test, y_test) = News20()
model = MLP(n_layers=5, activation='softsign', use_softmax=False)
optimizer = tf.keras.optimizers.Adagrad(lr=lr)
elif dataset == 'CIFAR-10':
(x_train, y_train), (x_test, y_test) = Cifar10()
model = CNN(use_softmax=False)
optimizer = tf.keras.optimizers.Adam(lr=lr)
else:
raise ValueError('Error: unknown dataset')
if pretrain == 'pretrain':
# Override optimizer
optimizer = tf.keras.optimizers.Adagrad(lr=lr)
lossstr = '-pretrain'
elif func_loss is loss.puloss:
lossstr = '-uPU'
elif func_loss is loss.nnpuloss:
lossstr = '-nnPU'
elif func_loss is loss.positive_risk:
lossstr = '-pRisk'
else:
raise ValueError('Error: unknown loss')
foldername = dataset + lossstr
if os.path.isdir('logs/' + foldername):
print('Error: log dir exist')
exit(2)
# prior probability
pi_p = np.count_nonzero(y_train) / y_train.size
loss.pi_p = pi_p
# choose first 1000 samples as training samples
n_p, n_n = 1000, y_train.size
# randomly choose n_p training samples as positive samples
# the rest is unlabeled samples
p_index = np.random.choice(y_train.sum(), n_p)
train_data_x = np.concatenate((x_train[y_train][p_index], x_train))
train_data_y = np.concatenate((np.ones(n_p), np.zeros(n_n)))
# normalize the training data and the test data
train_data_x, x_test = train_data_x / 255.0, x_test / 255.0
model.compile(
optimizer=optimizer,
loss=func_loss,
metrics=['acc', loss.positive_risk, loss.negative_risk, loss.error])
# TensorBoard visualization
tensorboard = tf.keras.callbacks.TensorBoard(
log_dir="logs/{}/train".format(foldername))
summary_writer = tf.summary.FileWriter("logs/{}/test".format(foldername))
callbacks = [tensorboard]
# Pretrain related
if pretrain == 'pretrain':
saver = tf.keras.callbacks.ModelCheckpoint('checkpoint/model.ckpt',
monitor='loss',
verbose=1,
save_best_only=True,
save_weights_only=True)
callbacks.append(saver)
elif pretrain == 'finetune':
model.load_weights("checkpoint/model.ckpt")
for i in range(10000):
model.fit(train_data_x,
train_data_y,
batch_size=batch_size,
epochs=i + 1,
shuffle=True,
callbacks=callbacks,
initial_epoch=i)
lossval, acc, prisk, nrisk, err = model.evaluate(x_test,
y_test,
batch_size=batch_size)
summary = tf.Summary()
summary.value.add(tag='test-loss', simple_value=lossval)
summary.value.add(tag='test-accuracy', simple_value=acc)
summary.value.add(tag='test-positive-risk', simple_value=prisk)
summary.value.add(tag='test-negative-risk', simple_value=nrisk)
summary.value.add(tag='test-error', simple_value=err)
summary_writer.add_summary(summary, i)
summary_writer.flush()
