def main(cuda, batch_size, pretrain_epochs, finetune_epochs):
writer = SummaryWriter() # create the TensorBoard object
# callback function to call during training, uses writer from the scope
def training_callback(epoch, lr, loss, validation_loss):
writer.add_scalars('data/autoencoder', {
'lr': lr,
'loss': loss,
'validation_loss': validation_loss,
}, epoch)
ds_train = CachedMNIST(train=True, cuda=cuda) # training dataset
ds_val = CachedMNIST(train=False, cuda=cuda) # evaluation dataset
autoencoder = StackedDenoisingAutoEncoder([28 * 28, 500, 500, 2000, 10],
final_activation=None)
if cuda:
autoencoder.cuda()
print('Pretraining stage.')
ae.pretrain(
ds_train,
autoencoder,
cuda=cuda,
validation=ds_val,
epochs=pretrain_epochs,
batch_size=batch_size,
optimizer=lambda model: SGD(model.parameters(), lr=0.1, momentum=0.9),
scheduler=lambda x: StepLR(x, 100, gamma=0.1),
corruption=0.2)
print('Training stage.')
ae_optimizer = SGD(params=autoencoder.parameters(), lr=0.1, momentum=0.9)
ae.train(ds_train,
autoencoder,
cuda=cuda,
validation=ds_val,
epochs=finetune_epochs,
batch_size=batch_size,
optimizer=ae_optimizer,
scheduler=StepLR(ae_optimizer, 100, gamma=0.1),
corruption=0.2,
update_callback=training_callback)
print('k-Means stage')
dataloader = DataLoader(ds_train, batch_size=1024, shuffle=False)
kmeans = KMeans(n_clusters=10, n_init=20)
autoencoder.eval()
features = []
actual = []
for index, batch in enumerate(dataloader):
if (isinstance(batch, tuple)
or isinstance(batch, list)) and len(batch) == 2:
batch, value = batch # if we have a prediction label, separate it to actual
actual.append(value)
if cuda:
batch = batch.cuda(async=True)
batch = batch.squeeze(1).view(batch.size(0), -1)
features.append(autoencoder.encoder(batch).detach().cpu())
actual = torch.cat(actual).long().cpu().numpy()
predicted = kmeans.fit_predict(torch.cat(features).numpy())
reassignment, accuracy = cluster_accuracy(predicted, actual)
print('Final k-Means accuracy: %s' % accuracy)
predicted_reassigned = [reassignment[item]
for item in predicted] # TODO numpify
confusion = confusion_matrix(actual, predicted_reassigned)
normalised_confusion = confusion.astype('float') / confusion.sum(
axis=1)[:, np.newaxis]
confusion_id = uuid.uuid4().hex
sns.heatmap(normalised_confusion).get_figure().savefig('confusion_%s.png' %
confusion_id)
print('Writing out confusion diagram with UUID: %s' % confusion_id)
writer.add_embedding(
torch.cat(features),
metadata=predicted,
label_img=ds_train.ds.train_data.float().unsqueeze(1), # TODO bit ugly
tag='predicted')
writer.close()
class SDAETransformerBase(TransformerMixin, BaseEstimator):
def __init__(self,
dimensions: List[int],
cuda: Optional[bool] = None,
batch_size: int = 256,
pretrain_epochs: int = 200,
finetune_epochs: int = 500,
corruption: Optional[float] = 0.2,
optimiser_pretrain: Callable[[torch.nn.Module], torch.optim.Optimizer] = lambda x: SGD(x.parameters(), lr=0.1, momentum=0.9),
optimiser_train: Callable[[torch.nn.Module], torch.optim.Optimizer] = lambda x: SGD(x.parameters(), lr=0.1, momentum=0.9),
scheduler: Optional[Callable[[torch.optim.Optimizer], Any]] = lambda x: StepLR(x, 100, gamma=0.1),
final_activation: Optional[torch.nn.Module] = None) -> None:
self.cuda = torch.cuda.is_available() if cuda is None else cuda
self.batch_size = batch_size
self.dimensions = dimensions
self.pretrain_epochs = pretrain_epochs
self.finetune_epochs = finetune_epochs
self.optimiser_pretrain = optimiser_pretrain
self.optimiser_train = optimiser_train
self.scheduler = scheduler
self.corruption = corruption
self.autoencoder = None
self.final_activation = final_activation
def fit(self, X, y=None):
if issparse(X):
X = X.todense()
ds = TensorDataset(torch.from_numpy(X.astype(np.float32)))
self.autoencoder = StackedDenoisingAutoEncoder(self.dimensions, final_activation=self.final_activation)
if self.cuda:
self.autoencoder.cuda()
ae.pretrain(
ds,
self.autoencoder,
cuda=self.cuda,
epochs=self.pretrain_epochs,
batch_size=self.batch_size,
optimizer=self.optimiser_pretrain,
scheduler=self.scheduler,
corruption=0.2,
silent=True
)
ae_optimizer = self.optimiser_train(self.autoencoder)
ae.train(
ds,
self.autoencoder,
cuda=self.cuda,
epochs=self.finetune_epochs,
batch_size=self.batch_size,
optimizer=ae_optimizer,
scheduler=self.scheduler(ae_optimizer),
corruption=self.corruption,
silent=True
)
return self
def score(self, X, y=None, sample_weight=None) -> float:
loss_function = torch.nn.MSELoss()
if self.autoencoder is None:
raise NotFittedError
if issparse(X):
X = X.todense()
self.autoencoder.eval()
ds = TensorDataset(torch.from_numpy(X.astype(np.float32)))
dataloader = DataLoader(
ds,
batch_size=self.batch_size,
shuffle=False
)
loss = 0
for index, batch in enumerate(dataloader):
batch = batch[0]
if self.cuda:
batch = batch.cuda(non_blocking=True)
output = self.autoencoder(batch)
loss += float(loss_function(output, batch).item())
return loss
# pretrain
ptsdae.model.pretrain(dataset,
autoencoder=ae,
epochs=args.pretrain_epochs,
batch_size=args.batch_size,
optimizer=get_opt,
scheduler=get_sched,
validation=validation,
update_freq=args.pretrain_epochs // 50,
cuda=True,
num_workers=args.njobs)
# train
# prep for cuda usage ...
ae.cuda()
# get our scheduler and optimizers
opt = get_opt(ae, lr=args.train_lr)
sched = get_sched(opt)
print("Training ...")
sys.stdout.flush()
ptsdae.model.train(dataset,
autoencoder=ae,
epochs=args.train_epochs,
batch_size=args.batch_size,
optimizer=opt,
scheduler=sched,
validation=validation,
update_freq=args.train_epochs // 50,
pretrain_epochs = 300
finetune_epochs = 500
training_callback = None
cuda = torch.cuda.is_available()
ds_val = None
embedded_dim = get_embedded_dim()
try:
autoencoder = pickle.load(open(autoencoder_path, 'rb'))
except:
autoencoder = StackedDenoisingAutoEncoder(
dimensions=[embedded_dim, 500, 500, 2000, 10],
final_activation=None,
)
if cuda:
autoencoder.cuda()
print('SDAE Pretraining stage.', flush=True)
print(f'@ {time.time() - start_time}\n', flush=True)
ae.pretrain(
ds_train,
autoencoder,
cuda=cuda,
validation=ds_val,
epochs=pretrain_epochs,
batch_size=batch_size,
optimizer=lambda model: SGD(
model.parameters(), lr=0.1, momentum=0.9),
scheduler=lambda x: StepLR(x, 100, gamma=0.1),
corruption=0.2,
silent=True,
def main(cuda, batch_size, pretrain_epochs, finetune_epochs, testing_mode):
writer = SummaryWriter() # create the TensorBoard object
# callback function to call during training, uses writer from the scope
def training_callback(epoch, lr, loss, validation_loss):
writer.add_scalars(
"data/autoencoder",
{
"lr": lr,
"loss": loss,
"validation_loss": validation_loss,
},
epoch,
)
ds_train = CachedMNIST(train=True, cuda=cuda,
testing_mode=testing_mode) # training dataset
ds_val = CachedMNIST(train=False, cuda=cuda,
testing_mode=testing_mode) # evaluation dataset
autoencoder = StackedDenoisingAutoEncoder([28 * 28, 500, 500, 2000, 10],
final_activation=None)
if cuda:
autoencoder.cuda()
print("Pretraining stage.")
ae.pretrain(
ds_train,
autoencoder,
cuda=cuda,
validation=ds_val,
epochs=pretrain_epochs,
batch_size=batch_size,
optimizer=lambda model: SGD(model.parameters(), lr=0.1, momentum=0.9),
scheduler=lambda x: StepLR(x, 100, gamma=0.1),
corruption=0.2,
)
print("Training stage.")
ae_optimizer = SGD(params=autoencoder.parameters(), lr=0.1, momentum=0.9)
ae.train(
ds_train,
autoencoder,
cuda=cuda,
validation=ds_val,
epochs=finetune_epochs,
batch_size=batch_size,
optimizer=ae_optimizer,
scheduler=StepLR(ae_optimizer, 100, gamma=0.1),
corruption=0.2,
update_callback=training_callback,
)
print("DEC stage.")
model = DEC(cluster_number=10,
hidden_dimension=10,
encoder=autoencoder.encoder)
if cuda:
model.cuda()
dec_optimizer = SGD(model.parameters(), lr=0.01, momentum=0.9)
train(
dataset=ds_train,
model=model,
epochs=100,
batch_size=256,
optimizer=dec_optimizer,
stopping_delta=0.000001,
cuda=cuda,
)
predicted, actual = predict(ds_train,
model,
1024,
silent=True,
return_actual=True,
cuda=cuda)
actual = actual.cpu().numpy()
predicted = predicted.cpu().numpy()
reassignment, accuracy = cluster_accuracy(actual, predicted)
print("Final DEC accuracy: %s" % accuracy)
if not testing_mode:
predicted_reassigned = [reassignment[item]
for item in predicted] # TODO numpify
confusion = confusion_matrix(actual, predicted_reassigned)
normalised_confusion = (confusion.astype("float") /
confusion.sum(axis=1)[:, np.newaxis])
confusion_id = uuid.uuid4().hex
sns.heatmap(normalised_confusion).get_figure().savefig(
"confusion_%s.png" % confusion_id)
print("Writing out confusion diagram with UUID: %s" % confusion_id)
writer.close()