기계 번역으로 제공되는 번역입니다. 제공된 번역과 원본 영어의 내용이 상충하는 경우에는 영어 버전이 우선합니다.

PyTorch 교육 스크립트 수정

이 섹션에서는 PyTorch 교육 스크립트를 수정하여 자동 파티셔닝과 수동 파티셔닝을 위한 SageMaker 모델 병렬화 라이브러리를 구성하는 방법을 알아봅니다.

자동 파티셔닝은 기본적으로 활성화되어 있음을 유의하세요. 달리 지정하지 않는 한, 다음 스크립트는 자동 파티셔닝을 사용합니다.

다음과 같은 자동 분할 PyTorch

SageMaker의 모델 병렬 처리 라이브러리로 교육 스크립트를 실행하려면 다음과 같은 PyTorch 교육 스크립트 변경이 필요합니다.

SageMaker의 모델 병렬화 라이브러리 API에 대한 자세한 내용은 API 설명서를 참조하십시오.

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchnet.dataset import SplitDataset
from torchvision import datasets

import smdistributed.modelparallel.torch as smp

class GroupedNet(nn.Module):
    def __init__(self):
        super(GroupedNet, self).__init__()
        # define layers

    def forward(self, x):
        # define forward pass and return model outputs


# smdistributed: Define smp.step. Return any tensors needed outside.
@smp.step
def train_step(model, data, target):
    output = model(data)
    loss = F.nll_loss(output, target, reduction="mean")
    model.backward(loss)
    return output, loss


def train(model, device, train_loader, optimizer):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        # smdistributed: Move input tensors to the GPU ID used by the current process,
        # based on the set_device call.
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        # Return value, loss_mb is a StepOutput object
        _, loss_mb = train_step(model, data, target)

        # smdistributed: Average the loss across microbatches.
        loss = loss_mb.reduce_mean()

        optimizer.step()

# smdistributed: initialize the backend
smp.init()

# smdistributed: Set the device to the GPU ID used by the current process.
# Input tensors should be transferred to this device.
torch.cuda.set_device(smp.local_rank())
device = torch.device("cuda")

# smdistributed: Download only on a single process per instance.
# When this is not present, the file is corrupted by multiple processes trying
# to download and extract at the same time
dataset = datasets.MNIST("../data", train=True, download=False)

# smdistributed: Shard the dataset based on data-parallel ranks
if smp.dp_size() > 1:
    partitions_dict = {f"{i}": 1 / smp.dp_size() for i in range(smp.dp_size())}
    dataset = SplitDataset(dataset, partitions=partitions_dict)
    dataset.select(f"{smp.dp_rank()}")

# smdistributed: Set drop_last=True to ensure that batch size is always divisible
# by the number of microbatches
train_loader = torch.utils.data.DataLoader(dataset, batch_size=64, drop_last=True)

model = GroupedNet()
optimizer = optim.Adadelta(model.parameters(), lr=4.0)

# smdistributed: Use the DistributedModel container to provide the model
# to be partitioned across different ranks. For the rest of the script,
# the returned DistributedModel object should be used in place of
# the model provided for DistributedModel class instantiation.
model = smp.DistributedModel(model)
optimizer = smp.DistributedOptimizer(optimizer)

train(model, device, train_loader, optimizer)

수동 분할은 다음과 같습니다. PyTorch

smp.partition 컨텍스트 관리자를 사용하여 특정 디바이스에 모듈을 배치합니다. smp.partition 컨텍스트에 배치되지 않은 모든 모듈은 default_partition에 배치됩니다. auto_partition가 False로 설정된 경우 default_partition을 제공해야 합니다. 특정 smp.partition 컨텍스트 내에서 생성된 모듈은 해당 파티션에 배치됩니다.

SageMaker의 모델 병렬화 라이브러리 API에 대한 자세한 내용은 API 설명서를 참조하십시오.

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchnet.dataset import SplitDataset
from torchvision import datasets

import smdistributed.modelparallel.torch as smp

class GroupedNet(nn.Module):
    def __init__(self):
        super(GroupedNet, self).__init__()
        with smp.partition(0):
            # define child modules on device 0
        with smp.partition(1):
            # define child modules on device 1

    def forward(self, x):
        # define forward pass and return model outputs


# smdistributed: Define smp.step. Return any tensors needed outside.
@smp.step
def train_step(model, data, target):
    output = model(data)
    loss = F.nll_loss(output, target, reduction="mean")
    model.backward(loss)
    return output, loss


def train(model, device, train_loader, optimizer):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        # smdistributed: Move input tensors to the GPU ID used by the current process,
        # based on the set_device call.
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        # Return value, loss_mb is a StepOutput object
        _, loss_mb = train_step(model, data, target)

        # smdistributed: Average the loss across microbatches.
        loss = loss_mb.reduce_mean()

        optimizer.step()

# smdistributed: initialize the backend
smp.init()

# smdistributed: Set the device to the GPU ID used by the current process.
# Input tensors should be transferred to this device.
torch.cuda.set_device(smp.local_rank())
device = torch.device("cuda")

# smdistributed: Download only on a single process per instance.
# When this is not present, the file is corrupted by multiple processes trying
# to download and extract at the same time
dataset = datasets.MNIST("../data", train=True, download=False)

# smdistributed: Shard the dataset based on data-parallel ranks
if smp.dp_size() > 1:
    partitions_dict = {f"{i}": 1 / smp.dp_size() for i in range(smp.dp_size())}
    dataset = SplitDataset(dataset, partitions=partitions_dict)
    dataset.select(f"{smp.dp_rank()}")

# smdistributed: Set drop_last=True to ensure that batch size is always divisible
# by the number of microbatches
train_loader = torch.utils.data.DataLoader(dataset, batch_size=64, drop_last=True)

model = GroupedNet()
optimizer = optim.Adadelta(model.parameters(), lr=4.0)

# smdistributed: Use the DistributedModel container to provide the model
# to be partitioned across different ranks. For the rest of the script,
# the returned DistributedModel object should be used in place of
# the model provided for DistributedModel class instantiation.
model = smp.DistributedModel(model)
optimizer = smp.DistributedOptimizer(optimizer)

train(model, device, train_loader, optimizer)

고려 사항

SageMaker의 모델 병렬화 라이브러리를 사용하여 PyTorch 교육 스크립트를 구성할 때는 다음 사항을 숙지해야 합니다.

지원되지 않는 프레임워크 기능

의 모델 병렬화 PyTorch 라이브러리에서는 다음 기능을 지원하지 않습니다. SageMaker