github.com/NVIDIA/aistore@v1.3.23-0.20240517131212-7df6609be51d/docs/examples/etl-imagenet-wd/pytorch_wd.py

import argparse
import os
import random
import shutil
import time
import warnings

import aistore
from aistore.client import Bck, Client
from aistore.client.transform import WDTransform

import webdataset as wds

import torch
import torch.nn as nn
import torch.nn.parallel
import torch.backends.cudnn as cudnn
import torch.optim
import torch.utils.data
import torch.utils.data.distributed
import torchvision.models as models
import torchvision.transforms as transforms

model_names = sorted(
    name
    for name in models.__dict__
    if name.islower() and not name.startswith("__") and callable(models.__dict__[name])
)

parser = argparse.ArgumentParser(description="PyTorch ImageNet Training")
parser.add_argument(
    "-a",
    "--arch",
    metavar="ARCH",
    default="resnet18",
    choices=model_names,
    help="model architecture: " + " | ".join(model_names) + " (default: resnet18)",
)
parser.add_argument(
    "-j",
    "--workers",
    default=4,
    type=int,
    metavar="N",
    help="number of data loading workers (default: 4)",
)
parser.add_argument(
    "--epochs",
    default=90,
    type=int,
    metavar="N",
    help="number of total epochs to run",
)
parser.add_argument(
    "--start-epoch",
    default=0,
    type=int,
    metavar="N",
    help="manual epoch number (useful on restarts)",
)
parser.add_argument(
    "-b",
    "--batch-size",
    default=256,
    type=int,
    metavar="N",
    help="mini-batch size (default: 256), this is the total "
    "batch size of all GPUs on the current node when "
    "using Data Parallel or Distributed Data Parallel",
)
parser.add_argument(
    "--lr",
    "--learning-rate",
    default=0.1,
    type=float,
    metavar="LR",
    help="initial learning rate",
    dest="lr",
)
parser.add_argument("--momentum", default=0.9, type=float, metavar="M", help="momentum")
parser.add_argument(
    "--wd",
    "--weight-decay",
    default=1e-4,
    type=float,
    metavar="W",
    help="weight decay (default: 1e-4)",
    dest="weight_decay",
)
parser.add_argument(
    "-p",
    "--print-freq",
    default=10,
    type=int,
    metavar="N",
    help="print frequency (default: 10)",
)
parser.add_argument(
    "--resume",
    default="",
    type=str,
    metavar="PATH",
    help="path to latest checkpoint (default: none)",
)
parser.add_argument(
    "-e",
    "--evaluate",
    dest="evaluate",
    action="store_true",
    help="evaluate model on validation set",
)
parser.add_argument(
    "--pretrained",
    dest="pretrained",
    action="store_true",
    help="use pre-trained model",
)
parser.add_argument(
    "--seed", default=None, type=int, help="seed for initializing training"
)
parser.add_argument("--gpu", default=None, type=int, help="GPU id to use.")
parser.add_argument(
    "--train-shards",
    default="imagenet-train-{000000..000005}.tar",
    type=str,
    help="template for shards to use for training",
)
parser.add_argument(
    "--val-shards",
    default="imagenet-train-{000000..000005}.tar",
    type=str,
    help="template for shards to use for validation",
)
parser.add_argument(
    "--ais-endpoint",
    default="http://aistore-sample-proxy:51080",
    type=str,
    help="AIStore proxy endpoint",
)
parser.add_argument(
    "--bucket-name", default="imagenet", type=str, help="dataset bucket name"
)
parser.add_argument(
    "--bucket-provider",
    default="ais",
    type=str,
    help='bucket provider (eg. "gcp", "aws", "ais")',
)

best_acc1 = 0


def main():
    args = parser.parse_args()

    if args.seed is not None:
        random.seed(args.seed)
        torch.manual_seed(args.seed)
        cudnn.deterministic = True
        warnings.warn(
            "You have chosen to seed training. "
            "This will turn on the CUDNN deterministic setting, "
            "which can slow down your training considerably! "
            "You may see unexpected behavior when restarting "
            "from checkpoints."
        )

    if args.gpu is not None:
        warnings.warn(
            "You have chosen a specific GPU. This will completely "
            "disable data parallelism."
        )

    ngpus_per_node = torch.cuda.device_count()
    main_worker(args.gpu, ngpus_per_node, args)


def wd_transform(client, pytorch_transform, name):
    def transform(sample):
        sample["npy"] = (
            pytorch_transform(sample.pop("jpg"))
            .permute(1, 2, 0)
            .numpy()
            .astype("float32")
        )
        return sample

    return WDTransform(client, transform, transform_name=name, verbose=True)


def loader(urls, batch_size, workers):
    to_tensor = transforms.Compose([transforms.ToTensor()])
    etl_dataset = (
        wds.WebDataset(urls, handler=wds.handlers.warn_and_continue)
        .decode("rgb")
        .to_tuple("npy cls", handler=wds.handlers.warn_and_continue)
        .map_tuple(to_tensor, lambda x: x)
    )
    ds_size = (500 * len(urls)) // batch_size
    etl_dataset = etl_dataset.with_length(ds_size)
    loader = wds.WebLoader(
        etl_dataset,
        batch_size=batch_size,
        num_workers=workers,
    )
    return loader.with_length(ds_size)


def main_worker(gpu, ngpus_per_node, args):
    global best_acc1
    args.gpu = gpu

    if args.gpu is not None:
        print("Use GPU: {} for training".format(args.gpu))

    # create model
    if args.pretrained:
        print("=> using pre-trained model '{}'".format(args.arch))
        model = models.__dict__[args.arch](pretrained=True)
    else:
        print("=> creating model '{}'".format(args.arch))
        model = models.__dict__[args.arch]()

    if not torch.cuda.is_available():
        print("using CPU, this will be slow")
    elif args.gpu is not None:
        torch.cuda.set_device(args.gpu)
        model = model.cuda(args.gpu)
    else:
        # DataParallel will divide and allocate batch_size to all available GPUs
        if args.arch.startswith("alexnet") or args.arch.startswith("vgg"):
            model.features = torch.nn.DataParallel(model.features)
            model.cuda()
        else:
            model = torch.nn.DataParallel(model).cuda()

    # define loss function (criterion) and optimizer
    criterion = nn.CrossEntropyLoss().cuda(args.gpu)

    optimizer = torch.optim.SGD(
        model.parameters(),
        args.lr,
        momentum=args.momentum,
        weight_decay=args.weight_decay,
    )

    # optionally resume from a checkpoint
    if args.resume:
        if os.path.isfile(args.resume):
            print("=> loading checkpoint '{}'".format(args.resume))
            if args.gpu is None:
                checkpoint = torch.load(args.resume)
            else:
                # Map model to be loaded to specified single gpu.
                loc = "cuda:{}".format(args.gpu)
                checkpoint = torch.load(args.resume, map_location=loc)
            args.start_epoch = checkpoint["epoch"]
            best_acc1 = checkpoint["best_acc1"]
            if args.gpu is not None:
                # best_acc1 may be from a checkpoint from a different GPU
                best_acc1 = best_acc1.to(args.gpu)
            model.load_state_dict(checkpoint["state_dict"])
            optimizer.load_state_dict(checkpoint["optimizer"])
            print(
                "=> loaded checkpoint '{}' (epoch {})".format(
                    args.resume, checkpoint["epoch"]
                )
            )
        else:
            print("=> no checkpoint found at '{}'".format(args.resume))

    cudnn.benchmark = True

    normalize = transforms.Normalize(
        mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]
    )

    client = Client(args.ais_endpoint)
    bck = Bck(args.bucket_name, provider=args.bucket_provider)

    train_transform = transforms.Compose(
        [
            transforms.RandomResizedCrop(224),
            transforms.RandomHorizontalFlip(),
            transforms.ToTensor(),
            normalize,
        ]
    )

    train_etl = wd_transform(client, train_transform, "img-train")
    train_urls = client.expand_object_urls(
        bck, transform_id=train_etl.uuid, template=args.train_shards
    )
    train_loader = loader(train_urls, args.batch_size, args.workers)

    val_transform = transforms.Compose(
        [
            transforms.Resize(256),
            transforms.CenterCrop(224),
            transforms.ToTensor(),
            normalize,
        ]
    )
    val_etl = wd_transform(client, val_transform, "img-val")
    val_urls = client.expand_object_urls(
        bck, transform_id=val_etl.uuid, template=args.val_shards
    )
    val_loader = loader(val_urls, args.batch_size, args.workers)

    if args.evaluate:
        validate(val_loader, model, criterion, args)
        return

    for epoch in range(args.start_epoch, args.epochs):
        adjust_learning_rate(optimizer, epoch, args)

        # train for one epoch
        train(train_loader, model, criterion, optimizer, epoch, args)

        # evaluate on validation set
        acc1 = validate(val_loader, model, criterion, args)

        # remember best acc@1 and save checkpoint
        is_best = acc1 > best_acc1
        best_acc1 = max(acc1, best_acc1)

        save_checkpoint(
            {
                "epoch": epoch + 1,
                "arch": args.arch,
                "state_dict": model.state_dict(),
                "best_acc1": best_acc1,
                "optimizer": optimizer.state_dict(),
            },
            is_best,
        )


def train(train_loader, model, criterion, optimizer, epoch, args):
    batch_time = AverageMeter("Time", ":6.3f")
    data_time = AverageMeter("Data", ":6.3f")
    losses = AverageMeter("Loss", ":.4e")
    top1 = AverageMeter("Acc@1", ":6.2f")
    top5 = AverageMeter("Acc@5", ":6.2f")
    progress = ProgressMeter(
        len(train_loader),
        [batch_time, data_time, losses, top1, top5],
        prefix="Epoch: [{}]".format(epoch),
    )

    # switch to train mode
    model.train()

    end = time.time()
    for i, (images, target) in enumerate(train_loader):
        # measure data loading time
        data_time.update(time.time() - end)

        if args.gpu is not None:
            images = images.cuda(args.gpu, non_blocking=True)
        if torch.cuda.is_available():
            target = target.cuda(args.gpu, non_blocking=True)

        # compute output
        output = model(images)
        loss = criterion(output, target)

        # measure accuracy and record loss
        acc1, acc5 = accuracy(output, target, topk=(1, 5))
        losses.update(loss.item(), images.size(0))
        top1.update(acc1[0], images.size(0))
        top5.update(acc5[0], images.size(0))

        # compute gradient and do SGD step
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        if i % args.print_freq == 0:
            progress.display(i)


def validate(val_loader, model, criterion, args):
    batch_time = AverageMeter("Time", ":6.3f")
    losses = AverageMeter("Loss", ":.4e")
    top1 = AverageMeter("Acc@1", ":6.2f")
    top5 = AverageMeter("Acc@5", ":6.2f")
    progress = ProgressMeter(
        len(val_loader), [batch_time, losses, top1, top5], prefix="Test: "
    )

    # switch to evaluate mode
    model.eval()

    with torch.no_grad():
        end = time.time()
        for i, (images, target) in enumerate(val_loader):
            if args.gpu is not None:
                images = images.cuda(args.gpu, non_blocking=True)
            if torch.cuda.is_available():
                target = target.cuda(args.gpu, non_blocking=True)

            # compute output
            output = model(images)
            loss = criterion(output, target)

            # measure accuracy and record loss
            acc1, acc5 = accuracy(output, target, topk=(1, 5))
            losses.update(loss.item(), images.size(0))
            top1.update(acc1[0], images.size(0))
            top5.update(acc5[0], images.size(0))

            # measure elapsed time
            batch_time.update(time.time() - end)
            end = time.time()

            if i % args.print_freq == 0:
                progress.display(i)

        # TODO: this should also be done with the ProgressMeter
        print(
            " * Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}".format(top1=top1, top5=top5)
        )

    return top1.avg


def save_checkpoint(state, is_best, filename="checkpoint.pth.tar"):
    torch.save(state, filename)
    if is_best:
        shutil.copyfile(filename, "model_best.pth.tar")


class AverageMeter(object):
    """Computes and stores the average and current value"""

    def __init__(self, name, fmt=":f"):
        self.name = name
        self.fmt = fmt
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count

    def __str__(self):
        fmtstr = "{name} {val" + self.fmt + "} ({avg" + self.fmt + "})"
        return fmtstr.format(**self.__dict__)


class ProgressMeter(object):
    def __init__(self, num_batches, meters, prefix=""):
        self.batch_fmtstr = self._get_batch_fmtstr(num_batches)
        self.meters = meters
        self.prefix = prefix

    def display(self, batch):
        entries = [self.prefix + self.batch_fmtstr.format(batch)]
        entries += [str(meter) for meter in self.meters]
        print("\t".join(entries))

    def _get_batch_fmtstr(self, num_batches):
        num_digits = len(str(num_batches // 1))
        fmt = "{:" + str(num_digits) + "d}"
        return "[" + fmt + "/" + fmt.format(num_batches) + "]"


def adjust_learning_rate(optimizer, epoch, args):
    """Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
    lr = args.lr * (0.1 ** (epoch // 30))
    for param_group in optimizer.param_groups:
        param_group["lr"] = lr


def accuracy(output, target, topk=(1,)):
    """Computes the accuracy over the k top predictions for the specified values of k"""
    with torch.no_grad():
        maxk = max(topk)
        batch_size = target.size(0)

        _, pred = output.topk(maxk, 1, True, True)
        pred = pred.t()
        correct = pred.eq(target.view(1, -1).expand_as(pred))

        res = []
        for k in topk:
            correct_k = correct[:k].reshape(-1).float().sum(0, keepdim=True)
            res.append(correct_k.mul_(100.0 / batch_size))
        return res


if __name__ == "__main__":
    main()