def handler(event, context):
dataset_name = 's3'
bucket_name = "s3-10"
num_workers = 10
tmp_bucket = "tmp-params"
merged_bucket = "merged-params"
clear_bucket(tmp_bucket)
clear_bucket(merged_bucket)
# invoke functions
payload = dict()
payload['dataset'] = dataset_name
payload['bucket_name'] = bucket_name
payload['num_workers'] = num_workers
payload['tmp_bucket'] = tmp_bucket
payload['merged_bucket'] = merged_bucket
# invoke functions
lambda_client = boto3.client('lambda')
for i in range(num_workers):
payload['rank'] = i
payload['file'] = '{}_{}'.format(i, num_workers)
lambda_client.invoke(FunctionName='LR_higgs',
InvocationType='Event',
Payload=json.dumps(payload))
def handler(event, context):
dataset_name = 's3'
bucket_name = "s3-libsvm"
num_workers = 10
num_buckets = 1
tmp_bucket_prefix = "tmp-params"
merged_bucket_prefix = "merged-params"
for i in range(num_buckets):
clear_bucket("{}-{}".format(tmp_bucket_prefix, i))
clear_bucket("{}-{}".format(merged_bucket_prefix, i))
# invoke functions
payload = dict()
payload['dataset'] = dataset_name
payload['bucket_name'] = bucket_name
payload['num_workers'] = num_workers
payload['num_buckets'] = num_buckets
payload['tmp_bucket_prefix'] = tmp_bucket_prefix
payload['merged_bucket_prefix'] = merged_bucket_prefix
# invoke functions
lambda_client = boto3.client('lambda')
for i in range(num_workers):
payload['rank'] = i
payload['file'] = '{}_{}'.format(i, num_workers)
lambda_client.invoke(FunctionName='LR_higgs_multibucket', InvocationType='Event', Payload=json.dumps(payload))
def handler(event, context):
dataset_name = 'yfcc100m'
bucket_name = "yfcc100m-400"
num_workers = 10
tmp_bucket = "tmp-params"
merged_bucket = "merged-params"
num_epochs = 10
num_admm_epochs = 10
learning_rate = 0.1
batch_size = 500
lam = 0.01
rho = 0.01
num_classes = 2
num_features = 4096
pos_tag = "animal"
files_per_worker = 4
clear_bucket(tmp_bucket)
clear_bucket(merged_bucket)
# invoke functions
payload = dict()
payload['dataset'] = dataset_name
payload['bucket_name'] = bucket_name
payload['num_workers'] = num_workers
payload['tmp_bucket'] = tmp_bucket
payload['merged_bucket'] = merged_bucket
payload['num_epochs'] = num_epochs
payload['num_admm_epochs'] = num_admm_epochs
payload['learning_rate'] = learning_rate
payload['batch_size'] = batch_size
payload['lambda'] = lam
payload['rho'] = rho
payload['num_classes'] = num_classes
payload['num_features'] = num_features
payload['pos_tag'] = pos_tag
# invoke functions
lambda_client = boto3.client('lambda')
for i in range(num_workers):
payload['rank'] = i
start_file_index = i * files_per_worker
payload['file'] = ",".join(range(start_file_index + files_per_worker))
lambda_client.invoke(FunctionName='LR_higgs',
InvocationType='Event',
Payload=json.dumps(payload))
def handler(event, context):
dataset_name = 's3'
bucket_name = "s3-10"
num_workers = 10
tmp_bucket = "tmp-params"
merged_bucket = "merged-params"
num_epochs = 10
num_admm_epochs = 10
learning_rate = 0.1
batch_size = 10000
lam = 0.01
rho = 0.01
num_classes = 2
num_features = 30
clear_bucket(tmp_bucket)
clear_bucket(merged_bucket)
# invoke functions
payload = dict()
payload['dataset'] = dataset_name
payload['bucket_name'] = bucket_name
payload['num_workers'] = num_workers
payload['tmp_bucket'] = tmp_bucket
payload['merged_bucket'] = merged_bucket
payload['num_epochs'] = num_epochs
payload['num_admm_epochs'] = num_admm_epochs
payload['learning_rate'] = learning_rate
payload['batch_size'] = batch_size
payload['lambda'] = lam
payload['rho'] = rho
payload['num_classes'] = num_classes
payload['num_features'] = num_features
# invoke functions
lambda_client = boto3.client('lambda')
for i in range(num_workers):
payload['rank'] = i
payload['file'] = '{}_{}'.format(i, num_workers)
lambda_client.invoke(FunctionName='LR_higgs',
InvocationType='Event',
Payload=json.dumps(payload))
def main(event, context):
storage = event['storage']
if storage == "memcache":
from archived.elasticache.Memcached import memcached_init
from archived.elasticache.Memcached.clear_all import clear_all
memcache_location = event['elasticache']
endpoint = memcached_init(redis_location)
clear_all(endpoint)
if storage == "redis":
from archived.elasticache import redis_init
from archived.sync import clear_bucket
redis_location = event['elasticache']
grad_bucket = event['grad_bucket']
model_bucket = event['model_bucket']
endpoint = redis_init(redis_location)
clear_bucket(endpoint,grad_bucket)
clear_bucket(endpoint,model_bucket)
def handler(event, context):
start_time = time.time()
bucket = event['bucket_name']
worker_index = event['rank']
num_workers = event['num_workers']
key = event['file']
merged_bucket = event['merged_bucket']
num_epochs = event['num_epochs']
num_admm_epochs = event['num_admm_epochs']
learning_rate = event['learning_rate']
lam = event['lambda']
rho = event['rho']
batch_size = event['batch_size']
elasti_location = event['elasticache']
endpoint = memcached_init(elasti_location)
print('bucket = {}'.format(bucket))
print("file = {}".format(key))
print('number of workers = {}'.format(num_workers))
print('worker index = {}'.format(worker_index))
print('merge bucket = {}'.format(merged_bucket))
print('num epochs = {}'.format(num_epochs))
print('num admm epochs = {}'.format(num_admm_epochs))
print('learning rate = {}'.format(learning_rate))
print("lambda = {}".format(lam))
print("rho = {}".format(rho))
print("batch_size = {}".format(batch_size))
# read file from s3
file = get_object(bucket, key).read().decode('utf-8').split("\n")
print("read data cost {} s".format(time.time() - start_time))
# file_path = "../../dataset/agaricus_127d_train.libsvm"
# file = open(file_path).readlines()
parse_start = time.time()
dataset = DenseDatasetWithLines(file, num_features)
print("parse data cost {} s".format(time.time() - parse_start))
preprocess_start = time.time()
# Creating data indices for training and validation splits:
dataset_size = len(dataset)
indices = list(range(dataset_size))
split = int(np.floor(validation_ratio * dataset_size))
if shuffle_dataset:
np.random.seed(random_seed)
np.random.shuffle(indices)
train_indices, val_indices = indices[split:], indices[:split]
# Creating PT data samplers and loaders:
train_sampler = SubsetRandomSampler(train_indices)
valid_sampler = SubsetRandomSampler(val_indices)
train_loader = torch.utils.data.DataLoader(dataset,
batch_size=batch_size,
sampler=train_sampler)
validation_loader = torch.utils.data.DataLoader(dataset,
batch_size=batch_size,
sampler=valid_sampler)
print("preprocess data cost {} s, dataset size = {}".format(
time.time() - preprocess_start, dataset_size))
model = LogisticRegression(num_features, num_classes).double()
print("size of w = {}".format(model.linear.weight.data.size()))
z, u = initialize_z_and_u(model.linear.weight.data.size())
print("size of z = {}".format(z.shape))
print("size of u = {}".format(u.shape))
# Loss and Optimizer
# Softmax is internally computed.
# Set parameters to be updated.
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
# Training the Model
train_start = time.time()
stop = False
for admm_epoch in range(num_admm_epochs):
print("ADMM Epoch >>> {}".format(admm_epoch))
for epoch in range(num_epochs):
epoch_start = time.time()
epoch_loss = 0
for batch_index, (items, labels) in enumerate(train_loader):
# print("------worker {} epoch {} batch {}------".format(worker_index, epoch, batch_index))
batch_start = time.time()
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
# Forward + Backward + Optimize
optimizer.zero_grad()
outputs = model(items.double())
classify_loss = criterion(outputs, labels)
epoch_loss += classify_loss.data
u_z = torch.from_numpy(u).double() - torch.from_numpy(
z).double()
loss = classify_loss
for name, param in model.named_parameters():
if name.split('.')[-1] == "weight":
loss += rho / 2.0 * torch.norm(param + u_z, p=2)
#loss = classify_loss + rho / 2.0 * torch.norm(torch.sum(model.linear.weight, u_z))
optimizer.zero_grad()
loss.backward(retain_graph=True)
optimizer.step()
# Test the Model
test_start = time.time()
correct = 0
total = 0
test_loss = 0
for items, labels in validation_loader:
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
outputs = model(items.double())
test_loss += criterion(outputs, labels).data
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
test_time = time.time() - test_start
print(
'Epoch: [%d/%d], Step: [%d/%d], Time: %.4f, Loss: %.4f, epoch cost %.4f, '
'batch cost %.4f s: test cost %.4f s, '
'accuracy of the model on the %d test samples: %d %%, loss = %f'
% (epoch + 1, num_epochs, batch_index + 1,
len(train_indices) / batch_size, time.time() - train_start,
epoch_loss.data, time.time() - epoch_start,
time.time() - batch_start, test_time, len(val_indices),
100 * correct / total, test_loss / total))
w = model.linear.weight.data.numpy()
w_shape = w.shape
b = model.linear.bias.data.numpy()
b_shape = b.shape
u_shape = u.shape
w_and_b = np.concatenate((w.flatten(), b.flatten()))
u_w_b = np.concatenate((u.flatten(), w_and_b.flatten()))
cal_time = time.time() - epoch_start
print("Epoch {} calculation cost = {} s".format(epoch, cal_time))
sync_start = time.time()
postfix = str(admm_epoch)
u_w_b_merge = reduce_epoch(endpoint, u_w_b, merged_bucket, num_workers,
worker_index, postfix)
u_mean = u_w_b_merge[:u_shape[0] *
u_shape[1]].reshape(u_shape) / float(num_workers)
w_mean = u_w_b_merge[u_shape[0] * u_shape[1]:u_shape[0] * u_shape[1] +
w_shape[0] *
w_shape[1]].reshape(w_shape) / float(num_workers)
b_mean = u_w_b_merge[u_shape[0] * u_shape[1] +
w_shape[0] * w_shape[1]:].reshape(
b_shape[0]) / float(num_workers)
# model.linear.weight.data = torch.from_numpy(w)
model.linear.bias.data = torch.from_numpy(b_mean)
sync_time = time.time() - sync_start
print("Epoch {} synchronization cost {} s".format(epoch, sync_time))
#z, u, r, s = update_z_u(w, z, u, rho, num_workers, lam)
#stop = check_stop(ep_abs, ep_rel, r, s, dataset_size, num_features, w, z, u, rho)
#print("stop = {}".format(stop))
#z = num_workers * rho / (2 * lam + num_workers * rho) * (w + u_mean)
z = update_z(w_mean, u_mean, rho, num_workers, lam)
#print(z)
u = u + model.linear.weight.data.numpy() - z
#print(u)
# Test the Model
correct = 0
total = 0
test_loss = 0
for items, labels in validation_loader:
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
outputs = model(items.double())
test_loss += criterion(outputs, labels).data
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
print(
'Epoch: %d, time = %.4f, accuracy of the model on the %d test samples: %d %%, loss = %f'
% (epoch, time.time() - train_start, len(val_indices),
100 * correct / total, test_loss / total))
if worker_index == 0:
clear_bucket(endpoint)
end_time = time.time()
print("Elapsed time = {} s".format(end_time - start_time))
def handler(event, context):
start_time = time.time()
bucket = event['bucket_name']
worker_index = event['rank']
num_workers = event['num_workers']
key = event['file']
merged_bucket = event['merged_bucket']
num_classes = event['num_classes']
num_features = event['num_features']
pos_tag = event['pos_tag']
num_epochs = event['num_epochs']
learning_rate = event['learning_rate']
batch_size = event['batch_size']
elasti_location = event['elasticache']
endpoint = memcached_init(elasti_location)
print('bucket = {}'.format(bucket))
print("file = {}".format(key))
print('merged bucket = {}'.format(merged_bucket))
print('number of workers = {}'.format(num_workers))
print('worker index = {}'.format(worker_index))
print('num epochs = {}'.format(num_epochs))
print('learning rate = {}'.format(learning_rate))
print("batch size = {}".format(batch_size))
# read file from s3
file = get_object(bucket, key).read().decode('utf-8').split("\n")
print("read data cost {} s".format(time.time() - start_time))
parse_start = time.time()
dataset = DenseLibsvmDataset(file, num_features, pos_tag)
totol_count = dataset.__len__()
pos_count = 0
for i in range(totol_count):
if dataset.__getitem__(i)[1] == 1:
pos_count += 1
print("{} positive observations out of {}".format(pos_count, totol_count))
print("parse data cost {} s".format(time.time() - parse_start))
preprocess_start = time.time()
# Creating data indices for training and validation splits:
dataset_size = len(dataset)
indices = list(range(dataset_size))
split = int(np.floor(validation_ratio * dataset_size))
if shuffle_dataset:
np.random.seed(random_seed)
np.random.shuffle(indices)
train_indices, val_indices = indices[split:], indices[:split]
# Creating PT data samplers and loaders:
train_sampler = SubsetRandomSampler(train_indices)
valid_sampler = SubsetRandomSampler(val_indices)
train_loader = torch.utils.data.DataLoader(dataset,
batch_size=batch_size,
sampler=train_sampler)
validation_loader = torch.utils.data.DataLoader(dataset,
batch_size=batch_size,
sampler=valid_sampler)
print("preprocess data cost {} s".format(time.time() - preprocess_start))
model = SVM(num_features, num_classes)
# Loss and Optimizer
# Softmax is internally computed.
# Set parameters to be updated.
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
# Training the Model
train_start = time.time()
for epoch in range(num_epochs):
epoch_start = time.time()
epoch_loss = 0
cal_time = 0
sync_time = 0
for batch_index, (items, labels) in enumerate(train_loader):
batch_start = time.time()
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
# Forward + Backward + Optimize
optimizer.zero_grad()
outputs = model(items)
loss = criterion(outputs, labels)
epoch_loss += loss.data
loss.backward()
w_grad = model.linear.weight.grad.data.numpy()
w_grad_shape = w_grad.shape
b_grad = model.linear.bias.grad.data.numpy()
b_grad_shape = b_grad.shape
w_b_grad = np.concatenate((w_grad.flatten(), b_grad.flatten()))
cal_time += time.time() - batch_start
sync_start = time.time()
postfix = "{}_{}".format(epoch, batch_index)
w_b_grad_merge = reduce_batch(endpoint, w_b_grad, merged_bucket,
num_workers, worker_index, postfix)
w_grad_merge = \
w_b_grad_merge[:w_grad_shape[0] * w_grad_shape[1]].reshape(w_grad_shape) / float(num_workers)
b_grad_merge = \
w_b_grad_merge[w_grad_shape[0] * w_grad_shape[1]:].reshape(b_grad_shape[0]) / float(num_workers)
model.linear.weight.grad = Variable(torch.from_numpy(w_grad_merge))
model.linear.bias.grad = Variable(torch.from_numpy(b_grad_merge))
sync_time += time.time() - sync_start
optimizer.step()
# print('Epoch: [%d/%d], Step: [%d/%d], Time: %.4f, Loss: %.4f, epoch cost %.4f, '
# 'batch cost %.4f s: cal cost %.4f s communication cost %.4f s, '
# % (epoch + 1, num_epochs, batch_index, len(train_indices) / batch_size,
# time.time() - train_start, loss.data, time.time() - epoch_start,
# time.time() - batch_start, cal_time, sync_time))
# Test the Model
test_start = time.time()
correct = 0
total = 0
test_loss = 0
for items, labels in validation_loader:
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
outputs = model(items)
test_loss += criterion(outputs, labels).data
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
test_time = time.time() - test_start
print(
'Epoch %d has %d batches, time = %.4f, epoch cost %.4f s: '
'computation cost %.4f s communication cost %.4f s, '
'train loss = %.4f, test cost %.4f s, accuracy of the model on the %d test samples: %d %%, loss = %f'
% (epoch, batch_index, time.time() - train_start, time.time() -
epoch_start, cal_time, sync_time, epoch_loss, test_time,
len(val_indices), 100 * correct / total, test_loss / total))
if worker_index == 0:
clear_bucket(endpoint)
end_time = time.time()
print("Elapsed time = {} s".format(end_time - start_time))
def handler(event, context):
try:
start_time = time.time()
bucket_name = event['bucket_name']
worker_index = event['rank']
num_workers = event['num_workers']
key = event['file']
merged_bucket = event['merged_bucket']
num_features = event['num_features']
learning_rate = event["learning_rate"]
batch_size = event["batch_size"]
num_epochs = event["num_epochs"]
validation_ratio = event["validation_ratio"]
elasti_location = event['elasticache']
endpoint = memcached_init(elasti_location)
# read file from s3
file = get_object(bucket_name, key).read().decode('utf-8').split("\n")
print("read data cost {} s".format(time.time() - start_time))
parse_start = time.time()
dataset = SparseDatasetWithLines(file, num_features)
print("parse data cost {} s".format(time.time() - parse_start))
preprocess_start = time.time()
dataset_size = len(dataset)
indices = list(range(dataset_size))
split = int(np.floor(validation_ratio * dataset_size))
if shuffle_dataset:
np.random.seed(random_seed)
np.random.shuffle(indices)
train_indices, val_indices = indices[split:], indices[:split]
train_set = [dataset[i] for i in train_indices]
val_set = [dataset[i] for i in val_indices]
print("preprocess data cost {} s".format(time.time() -
preprocess_start))
lr = LogisticRegression(train_set, val_set, num_features, num_epochs,
learning_rate, batch_size)
# Training the Model
train_start = time.time()
for epoch in range(num_epochs):
epoch_start = time.time()
num_batches = math.floor(len(train_set) / batch_size)
print(f"worker {worker_index} epoch {epoch}")
for batch_idx in range(num_batches):
batch_start = time.time()
batch_ins, batch_label = lr.next_batch(batch_idx)
batch_grad = torch.zeros(lr.n_input, 1, requires_grad=False)
batch_bias = np.float(0)
train_loss = Loss()
train_acc = Accuracy()
for i in range(len(batch_ins)):
z = lr.forward(batch_ins[i])
h = lr.sigmoid(z)
loss = lr.loss(h, batch_label[i])
#print("z= {}, h= {}, loss = {}".format(z, h, loss))
train_loss.update(loss, 1)
train_acc.update(h, batch_label[i])
g = lr.backward(batch_ins[i], h.item(), batch_label[i])
batch_grad.add_(g)
batch_bias += np.sum(h.item() - batch_label[i])
batch_grad = batch_grad.div(len(batch_ins))
batch_bias = batch_bias / len(batch_ins)
batch_grad.mul_(-1.0 * learning_rate)
lr.grad.add_(batch_grad)
lr.bias = lr.bias - batch_bias * learning_rate
sync_start = time.time()
np_grad = lr.grad.numpy().flatten()
np_bias = np.array(lr.bias, dtype=np_grad.dtype)
w_and_b = np.concatenate((np_grad, np_bias))
postfix = "{}_{}".format(epoch, batch_idx)
w_b_merge = reduce_batch(endpoint, w_and_b, merged_bucket,
num_workers, worker_index, postfix)
lr.grad, lr.bias = w_b_merge[:-1].reshape(num_features, 1) / float(num_workers), \
float(w_b_merge[-1]) / float(num_workers)
sync_time = time.time() - sync_start
print("synchronization cost {}s, batch takes {}s".format(
sync_time,
time.time() - batch_start))
if (batch_idx + 1) % 10 == 0:
print("Epoch: {}/{}, Step: {}/{}, Loss: {}".format(
epoch + 1, num_epochs, batch_idx + 1, num_batches,
train_loss))
cal_time = time.time() - epoch_start
test_start = time.time()
val_loss, val_acc = lr.evaluate()
test_time = time.time() - test_start
print(
'Epoch: [%d/%d], Step: [%d/%d], Time: %.4f, Loss: %s, Accuracy: %s, epoch cost %.4f, '
'cal cost %.4f s, sync cost %.4f s, test cost %.4f s, '
'test accuracy: %s %%, test loss: %s' %
(epoch + 1, num_epochs, batch_idx + 1,
num_batches, time.time() - train_start, train_loss, train_acc,
time.time() - epoch_start, cal_time, sync_time, test_time,
val_acc, val_loss))
if worker_index == 0:
clear_bucket(endpoint)
print("elapsed time = {} s".format(time.time() - start_time))
except Exception as e:
print("Error {}".format(e))
def handler(event, context):
start_time = time.time()
bucket = event['bucket_name']
worker_index = event['rank']
num_workers = event['num_workers']
key = event['file'].split(",")
merged_bucket = event['merged_bucket']
num_classes = event['num_classes']
num_features = event['num_features']
pos_tag = event['pos_tag']
num_epochs = event['num_epochs']
num_admm_epochs = event['num_admm_epochs']
learning_rate = event['learning_rate']
batch_size = event['batch_size']
lam = event['lambda']
rho = event['rho']
elasti_location = event['elasticache']
endpoint = memcached_init(elasti_location)
print('bucket = {}'.format(bucket))
print("file = {}".format(key))
print('number of workers = {}'.format(num_workers))
print('worker index = {}'.format(worker_index))
print('merge bucket = {}'.format(merged_bucket))
print('num epochs = {}'.format(num_epochs))
print('num admm epochs = {}'.format(num_admm_epochs))
print('num classes = {}'.format(num_classes))
print('num features = {}'.format(num_features))
print('positive tag = {}'.format(pos_tag))
print('learning rate = {}'.format(learning_rate))
print("batch_size = {}".format(batch_size))
print("lambda = {}".format(lam))
print("rho = {}".format(rho))
# read file from s3
file = get_object(bucket, key[0]).read().decode('utf-8').split("\n")
dataset = DenseLibsvmDataset(file, num_features, pos_tag)
if len(key) > 1:
for more_key in key[1:]:
file = get_object(bucket,
more_key).read().decode('utf-8').split("\n")
dataset.add_more(file)
print("read data cost {} s".format(time.time() - start_time))
parse_start = time.time()
total_count = dataset.__len__()
pos_count = 0
for i in range(total_count):
if dataset.__getitem__(i)[1] == 1:
pos_count += 1
print("{} positive observations out of {}".format(pos_count, total_count))
print("parse data cost {} s".format(time.time() - parse_start))
preprocess_start = time.time()
# Creating data indices for training and validation splits:
dataset_size = len(dataset)
indices = list(range(dataset_size))
split = int(np.floor(validation_ratio * dataset_size))
if shuffle_dataset:
np.random.seed(random_seed)
np.random.shuffle(indices)
train_indices, val_indices = indices[split:], indices[:split]
# Creating PT data samplers and loaders:
train_sampler = SubsetRandomSampler(train_indices)
valid_sampler = SubsetRandomSampler(val_indices)
train_loader = torch.utils.data.DataLoader(dataset,
batch_size=batch_size,
sampler=train_sampler)
validation_loader = torch.utils.data.DataLoader(dataset,
batch_size=batch_size,
sampler=valid_sampler)
print("preprocess data cost {} s, dataset size = {}".format(
time.time() - preprocess_start, dataset_size))
model = SVM(num_features, num_classes).float()
print("size of w = {}".format(model.linear.weight.data.size()))
z, u = initialize_z_and_u(model.linear.weight.data.size())
print("size of z = {}".format(z.shape))
print("size of u = {}".format(u.shape))
# Loss and Optimizer
# Softmax is internally computed.
# Set parameters to be updated.
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
# Training the Model
train_start = time.time()
stop = False
for admm_epoch in range(num_admm_epochs):
admm_epoch_start = time.time()
for epoch in range(num_epochs):
epoch_start = time.time()
epoch_loss = 0
for batch_index, (items, labels) in enumerate(train_loader):
batch_start = time.time()
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
# Forward + Backward + Optimize
optimizer.zero_grad()
outputs = model(items)
classify_loss = torch.mean(
torch.clamp(1 - outputs.t() * labels.float(),
min=0)) # hinge loss
epoch_loss += classify_loss
u_z = torch.from_numpy(u).float() - torch.from_numpy(z).float()
loss = classify_loss
for name, param in model.named_parameters():
if name.split('.')[-1] == "weight":
loss += rho / 2.0 * torch.norm(param + u_z, p=2)
#loss = classify_loss + rho / 2.0 * torch.norm(torch.sum(model.linear.weight, u_z))
optimizer.zero_grad()
loss.backward(retain_graph=True)
optimizer.step()
# Test the Model
test_start = time.time()
correct = 0
total = 0
test_loss = 0
for items, labels in validation_loader:
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
outputs = model(items)
test_loss += torch.mean(
torch.clamp(1 - outputs.t() * labels.float(), min=0))
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
test_time = time.time() - test_start
print(
'ADMM Epoch: [%d/%d], Epoch: [%d/%d], Batch [%d], '
'Time: %.4f, Loss: %.4f, epoch cost %.4f, test cost %.4f s, '
'accuracy of the model on the %d test samples: %d %%, loss = %f'
% (admm_epoch, num_admm_epochs, epoch, num_epochs, batch_index,
time.time() - train_start,
epoch_loss.data, time.time() - epoch_start, test_time,
len(val_indices), 100 * correct / total, test_loss / total))
w = model.linear.weight.data.numpy()
w_shape = w.shape
b = model.linear.bias.data.numpy()
b_shape = b.shape
u_shape = u.shape
w_and_b = np.concatenate((w.flatten(), b.flatten()))
u_w_b = np.concatenate((u.flatten(), w_and_b.flatten()))
cal_time = time.time() - epoch_start
sync_start = time.time()
postfix = "{}".format(admm_epoch)
u_w_b_merge = reduce_epoch(endpoint, u_w_b, merged_bucket, num_workers,
worker_index, postfix)
u_mean = u_w_b_merge[:u_shape[0] *
u_shape[1]].reshape(u_shape) / float(num_workers)
w_mean = u_w_b_merge[u_shape[0] * u_shape[1]:u_shape[0] * u_shape[1] +
w_shape[0] *
w_shape[1]].reshape(w_shape) / float(num_workers)
b_mean = u_w_b_merge[u_shape[0] * u_shape[1] +
w_shape[0] * w_shape[1]:].reshape(
b_shape[0]) / float(num_workers)
#model.linear.weight.data = torch.from_numpy(w)
model.linear.bias.data = torch.from_numpy(b_mean).float()
sync_time = time.time() - sync_start
#z, u, r, s = update_z_u(w, z, u, rho, num_workers, lam)
#stop = check_stop(ep_abs, ep_rel, r, s, dataset_size, num_features, w, z, u, rho)
#print("stop = {}".format(stop))
#z = num_workers * rho / (2 * lam + num_workers * rho) * (w + u_mean)
z = update_z(w_mean, u_mean, rho, num_workers, lam)
#print(z)
u = u + model.linear.weight.data.numpy() - z
#print(u)
# Test the Model
test_start = time.time()
correct = 0
total = 0
test_loss = 0
for items, labels in validation_loader:
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
outputs = model(items)
test_loss += torch.mean(
torch.clamp(1 - outputs.t() * labels.float(), min=0))
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
test_time = time.time() - test_start
print(
'ADMM Epoch: [%d/%d], Time: %.4f, Loss: %.4f, '
'ADMM epoch cost %.4f: computation cost %.4f s communication cost %.4f s test cost %.4f s, '
'accuracy of the model on the %d test samples: %d %%, loss = %f' %
(admm_epoch,
num_admm_epochs, time.time() - train_start, epoch_loss.data,
time.time() - admm_epoch_start, cal_time, sync_time, test_time,
len(val_indices), 100 * correct / total, test_loss / total))
# Test the Model
correct = 0
total = 0
test_loss = 0
for items, labels in validation_loader:
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
outputs = model(items)
test_loss += torch.mean(
torch.clamp(1 - outputs.t() * labels.float(), min=0))
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
print(
'Time = %.4f, accuracy of the model on the %d test samples: %d %%, loss = %f'
% (time.time() - train_start, len(val_indices), 100 * correct / total,
test_loss / total))
if worker_index == 0:
clear_bucket(endpoint)
end_time = time.time()
print("Elapsed time = {} s".format(end_time - start_time))
def handler(event, context):
try:
start_time = time.time()
bucket_name = event['bucket_name']
worker_index = event['rank']
num_workers = event['num_workers']
key = event['file']
merged_bucket = event['merged_bucket']
num_features = event['num_features']
learning_rate = event["learning_rate"]
batch_size = event["batch_size"]
num_epochs = event["num_epochs"]
validation_ratio = event["validation_ratio"]
elasti_location = event['elasticache']
endpoint = memcached_init(elasti_location)
# Reading data from S3
print(f"Reading training data from bucket = {bucket_name}, key = {key}")
file = get_object(bucket_name, key).read().decode('utf-8').split("\n")
print("read data cost {} s".format(time.time() - start_time))
parse_start = time.time()
dataset = SparseDatasetWithLines(file, num_features)
print("parse data cost {} s".format(time.time() - parse_start))
preprocess_start = time.time()
dataset_size = len(dataset)
indices = list(range(dataset_size))
split = int(np.floor(validation_ratio * dataset_size))
if shuffle_dataset:
np.random.seed(random_seed)
np.random.shuffle(indices)
train_indices, val_indices = indices[split:], indices[:split]
train_set = [dataset[i] for i in train_indices]
val_set = [dataset[i] for i in val_indices]
print("preprocess data cost {} s".format(time.time() - preprocess_start))
svm = SparseSVM(train_set, val_set, num_features, num_epochs, learning_rate, batch_size)
# Training the Model
train_start = time.time()
for epoch in range(num_epochs):
epoch_start = time.time()
num_batches = math.floor(len(train_set) / batch_size)
print("worker {} epoch {}".format(worker_index, epoch))
for batch_idx in range(num_batches):
batch_start = time.time()
batch_ins, batch_label = svm.next_batch(batch_idx)
acc = svm.one_epoch(batch_idx, epoch)
if (batch_idx + 1) % 10 == 0:
print("Epoch: {}/{}, Step: {}/{}, train acc: {}"
.format(epoch + 1, num_epochs, batch_idx + 1, num_batches, acc))
cal_time = time.time() - epoch_start
sync_start = time.time()
np_w = svm.weights.numpy().flatten()
postfix = str(epoch)
w_merge = reduce_epoch(endpoint, np_w, merged_bucket, num_workers, worker_index, postfix)
svm.weights = torch.from_numpy(w_merge).reshape(num_features, 1)
sync_time = time.time() - sync_start
test_start = time.time()
val_acc = svm.evaluate()
test_time = time.time() - test_start
print('Epoch: [%d/%d], Step: [%d/%d], Time: %.4f, epoch cost %.4f, '
'cal cost %.4f s, sync cost %.4f s, test cost %.4f s, test accuracy: %s %%'
% (epoch + 1, num_epochs, batch_idx + 1, num_batches,
time.time() - train_start, time.time() - epoch_start,
cal_time, sync_time, test_time, val_acc))
if worker_index == 0:
clear_bucket(endpoint)
print("elapsed time = {} s".format(time.time() - start_time))
except Exception as e:
print("Error {}".format(e))
def handler(event, context):
startTs = time.time()
bucket = event['Records'][0]['s3']['bucket']['name']
key = urllib.parse.unquote_plus(event['Records'][0]['s3']['object']['key'], encoding='utf-8')
print('bucket = {}'.format(bucket))
print('key = {}'.format(key))
key_splits = key.split("_")
worker_index = int(key_splits[0])
num_worker = int(key_splits[1])
sync_meta = SyncMeta(worker_index, num_worker)
print("synchronization meta {}".format(sync_meta.__str__()))
# read file from s3
file = get_object(bucket, key).read().decode('utf-8').split("\n")
print("read data cost {} s".format(time.time() - startTs))
parse_start = time.time()
dataset = DenseDatasetWithLines(file, num_features)
print("parse data cost {} s".format(time.time() - parse_start))
preprocess_start = time.time()
# Creating data indices for training and validation splits:
dataset_size = len(dataset)
indices = list(range(dataset_size))
split = int(np.floor(validation_ratio * dataset_size))
if shuffle_dataset:
np.random.seed(random_seed)
np.random.shuffle(indices)
train_indices, val_indices = indices[split:], indices[:split]
# Creating PT data samplers and loaders:
train_sampler = SubsetRandomSampler(train_indices)
valid_sampler = SubsetRandomSampler(val_indices)
train_loader = torch.utils.data.DataLoader(dataset,
batch_size=batch_size,
sampler=train_sampler)
validation_loader = torch.utils.data.DataLoader(dataset,
batch_size=batch_size,
sampler=valid_sampler)
print("preprocess data cost {} s".format(time.time() - preprocess_start))
model = LogisticRegression(num_features, num_classes)
# Loss and Optimizer
# Softmax is internally computed.
# Set parameters to be updated.
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
# Training the Model
for epoch in range(num_epochs):
for batch_index, (items, labels) in enumerate(train_loader):
print("------worker {} epoch {} batch {}------".format(worker_index, epoch, batch_index))
batch_start = time.time()
items = Variable(items.view(-1, num_features))
labels = Variable(labels)
# Forward + Backward + Optimize
optimizer.zero_grad()
outputs = model(items)
loss = criterion(outputs, labels)
loss.backward()
print("forward and backward cost {} s".format(time.time()-batch_start))
w_grad = model.linear.weight.grad.data.numpy()
b_grad = model.linear.bias.grad.data.numpy()
#print("dtype of grad = {}".format(w_grad.dtype))
print("w_grad before merge = {}".format(w_grad[0][0:5]))
print("b_grad before merge = {}".format(b_grad))
sync_start = time.time()
put_object(grad_bucket, w_grad_prefix + str(worker_index), w_grad.tobytes())
put_object(grad_bucket, b_grad_prefix + str(worker_index), b_grad.tobytes())
file_postfix = "{}_{}".format(epoch, batch_index)
if worker_index == 0:
w_grad_merge, b_grad_merge = \
merge_w_b_grads(grad_bucket, num_worker, w_grad.dtype,
w_grad.shape, b_grad.shape,
w_grad_prefix, b_grad_prefix)
put_merged_w_b_grad(model_bucket, w_grad_merge, b_grad_merge,
file_postfix, w_grad_prefix, b_grad_prefix)
delete_expired_w_b(model_bucket, epoch, batch_index, w_grad_prefix, b_grad_prefix)
model.linear.weight.grad = Variable(torch.from_numpy(w_grad_merge))
model.linear.bias.grad = Variable(torch.from_numpy(b_grad_merge))
else:
w_grad_merge, b_grad_merge = get_merged_w_b_grad(model_bucket, file_postfix,
w_grad.dtype, w_grad.shape, b_grad.shape,
w_grad_prefix, b_grad_prefix)
model.linear.weight.grad = Variable(torch.from_numpy(w_grad_merge))
model.linear.bias.grad = Variable(torch.from_numpy(b_grad_merge))
print("w_grad after merge = {}".format(model.linear.weight.grad.data.numpy()[0][:5]))
print("b_grad after merge = {}".format(model.linear.bias.grad.data.numpy()))
print("synchronization cost {} s".format(time.time() - sync_start))
optimizer.step()
print("batch cost {} s".format(time.time() - batch_start))
if (batch_index + 1) % 10 == 0:
print('Epoch: [%d/%d], Step: [%d/%d], Loss: %.4f'
% (epoch + 1, num_epochs, batch_index + 1, len(train_indices) / batch_size, loss.data))
if worker_index == 0:
clear_bucket(model_bucket)
clear_bucket(grad_bucket)
# Test the Model
correct = 0
total = 0
for items, labels in validation_loader:
items = Variable(items.view(-1, num_features))
# items = Variable(items)
outputs = model(items)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
print('Accuracy of the model on the %d test samples: %d %%' % (len(val_indices), 100 * correct / total))
endTs = time.time()
print("elapsed time = {} s".format(endTs - startTs))
