def train(self, batch_size=1024, epochs=1, initial_epoch=0, verbose=1):
if batch_size >= self.node_size:
if batch_size > self.node_size:
print('batch_size({0}) > node_size({1}),set batch_size = {1}'.format(
batch_size, self.node_size))
batch_size = self.node_size
return self.model.fit([self.A, self.L], [self.A, self.L], batch_size=batch_size, epochs=epochs, initial_epoch=initial_epoch, verbose=verbose, shuffle=False)
else:
steps_per_epoch = (self.node_size - 1) // batch_size + 1
hist = History()
hist.on_train_begin()
logs = {}
for epoch in range(initial_epoch, epochs):
start_time = time.time()
losses = np.zeros(3)
for i in range(steps_per_epoch):
index = np.arange(i * batch_size, min((i + 1) * batch_size, self.node_size))
train_A = self.A[index, :] # batch_size * node_size
train_L = self.L[index][:, index] # L矩阵是一个对角矩阵
inp = [train_A, train_L]
batch_losses = self.model.train_on_batch(inp, inp)
losses += batch_losses
losses = losses / steps_per_epoch
logs['loss'] = losses[0]
logs['2nd_loss'] = losses[1]
logs['1st_loss'] = losses[2]
epoch_time = int(time.time() - start_time)
hist.on_epoch_end(epoch, logs)
if verbose > 0:
print('Epoch {0}/{1}'.format(epoch + 1, epochs))
print('{0}s - loss: {1: .4f} - 2nd_loss: {2: .4f} - 1st_loss: {3: .4f}'.format(
epoch_time, losses[0], losses[1], losses[2]))
return hist
def train(self, batch_size=1024, epochs=2, initial_epoch=0, verbose=1):
"""Train SDNE model.
Parameters
----------
batch_size : int, optional (default : 1024)
epochs : int, optional (default : 2)
inital_epoch : int, optional (default : 0)
verbose : int, optional (default : 1)
"""
from tensorflow.python.keras.callbacks import History
if batch_size >= self.node_size:
if batch_size > self.node_size:
print('batch_size({0}) > node_size({1}),set batch_size = {1}'.format(
batch_size, self.node_size))
batch_size = self.node_size
return self.model.fit([self.A.todense(), self.L.todense()], [self.A.todense(), self.L.todense()],
batch_size=batch_size, epochs=epochs, initial_epoch=initial_epoch, verbose=verbose,
shuffle=False, )
else:
steps_per_epoch = (self.node_size - 1) // batch_size + 1
hist = History()
hist.on_train_begin()
logs = {}
for epoch in range(initial_epoch, epochs):
start_time = time.time()
losses = np.zeros(3)
for i in range(steps_per_epoch):
index = np.arange(
i * batch_size, min((i + 1) * batch_size, self.node_size))
A_train = self.A[index, :].todense()
L_mat_train = self.L[index][:, index].todense()
inp = [A_train, L_mat_train]
batch_losses = self.model.train_on_batch(inp, inp)
losses += batch_losses
losses = losses / steps_per_epoch
logs['loss'] = losses[0]
logs['2nd_loss'] = losses[1]
logs['1st_loss'] = losses[2]
epoch_time = int(time.time() - start_time)
# TODO: Fixed the bug derivated by the following code in TF2:
# hist.on_epoch_end(epoch, logs)
if verbose > 0:
print('Epoch {0}/{1}'.format(epoch + 1, epochs))
print('{0}s - loss: {1: .4f} - 2nd_loss: {2: .4f} - 1st_loss: {3: .4f}'.format(
epoch_time, losses[0], losses[1], losses[2]))
return hist
def train(self, batch_size=1024, epochs=1, initial_epoch=0, verbose=1):
print(self.model.summary())
# return
if batch_size >= self.node_size:
if batch_size > self.node_size:
print('batch_size({0}) > node_size({1}), set batch_size = {1}'.
format(batch_size, self.node_size))
batch_size = self.node_size
return self.model.fit(
[self.A.todense(), self.L.todense()],
[self.A.todense(), self.L.todense()],
batch_size=batch_size,
epochs=epochs,
initial_epoch=initial_epoch,
verbose=verbose,
shuffle=False,
)
else:
steps_per_epoch = (self.node_size - 1) // batch_size + 1
hist = History()
hist.on_train_begin()
logs = {}
for epoch in range(initial_epoch, epochs):
start_time = time.time()
losses = np.zeros(3)
for i in range(steps_per_epoch):
index = np.arange(
i * batch_size,
min((i + 1) * batch_size, self.node_size))
A_train = self.A[index, :].todense()
L_mat_train = self.L[index][:, index].todense()
inp = [A_train, L_mat_train]
print("A_train: ", A_train)
print("L_mat_train: ", L_mat_train)
batch_losses = self.model.train_on_batch(inp, inp)
losses += batch_losses
losses = losses / steps_per_epoch
logs['loss'] = losses[0]
logs['2nd_loss'] = losses[1]
logs['1st_loss'] = losses[2]
epoch_time = int(time.time() - start_time)
hist.on_epoch_begin(epoch, logs)
if verbose > 0:
print('Epoch {0}/{1}'.format(epoch + 1, epochs))
print(
'{0}s - loss: {1: .4f} - 2nd_loss: {2: .4f} - 1st_lost: {3: .4f}'
.format(epoch_time, losses[0], losses[1], losses[2]))
return hist
