imagenet_1k_eval.py

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.

# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.

# Modified from https://github.com/pytorch/examples/blob/master/imagenet/main.py
# See https://github.com/pytorch/examples/tree/master/imagenet for usage.

import argparse
import os
import time
import warnings
from enum import Enum

import hubconf
import torch
import torch.distributed as dist
import torch.multiprocessing as mp
import torch.nn as nn
import torch.nn.parallel
import torch.optim
import torch.utils.data
import torch.utils.data.distributed
import torchvision.datasets as datasets
import torchvision.transforms as transforms


model_names = [
    name
    for name in hubconf.__dict__
    if "in1k" in name and callable(hubconf.__dict__[name])
]


parser = argparse.ArgumentParser(description="PyTorch ImageNet Training")
parser.add_argument("data", metavar="DIR", help="path to dataset")
parser.add_argument(
    "-m",
    "--model",
    metavar="MODEL",
    default="vit_b16_in1k",
    choices=model_names,
    help="model name: " + " | ".join(model_names) + " (default: vit_b16_in1k)",
)
parser.add_argument(
    "-r", "--resolution", default=224, type=int, help="input resolution of the images"
)
parser.add_argument(
    "-j",
    "--workers",
    default=4,
    type=int,
    metavar="N",
    help="number of data loading workers (default: 4)",
)
parser.add_argument(
    "-b",
    "--batch-size",
    default=200,
    type=int,
    metavar="N",
    help="mini-batch size (default: 200), this is the total "
    "batch size of all GPUs on the current node when "
    "using Data Parallel or Distributed Data Parallel",
)
parser.add_argument(
    "-p",
    "--print-freq",
    default=10,
    type=int,
    metavar="N",
    help="print frequency (default: 10)",
)
parser.add_argument(
    "--world-size",
    default=-1,
    type=int,
    help="number of nodes for distributed training",
)
parser.add_argument(
    "--rank", default=-1, type=int, help="node rank for distributed training"
)
parser.add_argument(
    "--dist-url",
    default="tcp://224.66.41.62:23456",
    type=str,
    help="url used to set up distributed training",
)
parser.add_argument(
    "--dist-backend", default="nccl", type=str, help="distributed backend"
)
parser.add_argument("--gpu", default=None, type=int, help="GPU id to use.")
parser.add_argument(
    "--multiprocessing-distributed",
    action="store_true",
    help="Use multi-processing distributed training to launch "
    "N processes per node, which has N GPUs. This is the "
    "fastest way to use PyTorch for either single node or "
    "multi node data parallel training",
)

best_acc1 = 0


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

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

    if args.dist_url == "env://" and args.world_size == -1:
        args.world_size = int(os.environ["WORLD_SIZE"])

    args.distributed = args.world_size > 1 or args.multiprocessing_distributed

    ngpus_per_node = torch.cuda.device_count()
    if args.multiprocessing_distributed:
        # Since we have ngpus_per_node processes per node, the total world_size
        # needs to be adjusted accordingly
        args.world_size = ngpus_per_node * args.world_size
        # Use torch.multiprocessing.spawn to launch distributed processes: the
        # main_worker process function
        mp.spawn(main_worker, nprocs=ngpus_per_node, args=(ngpus_per_node, args))
    else:
        # Simply call main_worker function
        main_worker(args.gpu, ngpus_per_node, args)


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))

    if args.distributed:
        if args.dist_url == "env://" and args.rank == -1:
            args.rank = int(os.environ["RANK"])
        if args.multiprocessing_distributed:
            # For multiprocessing distributed training, rank needs to be the
            # global rank among all the processes
            args.rank = args.rank * ngpus_per_node + gpu
        dist.init_process_group(
            backend=args.dist_backend,
            init_method=args.dist_url,
            world_size=args.world_size,
            rank=args.rank,
        )
    # create model
    model = torch.hub.load("./", args.model, source="local")

    if not torch.cuda.is_available():
        print("using CPU, this will be slow")
    elif args.distributed:
        # For multiprocessing distributed, DistributedDataParallel constructor
        # should always set the single device scope, otherwise,
        # DistributedDataParallel will use all available devices.
        if args.gpu is not None:
            torch.cuda.set_device(args.gpu)
            model.cuda(args.gpu)
            # When using a single GPU per process and per
            # DistributedDataParallel, we need to divide the batch size
            # ourselves based on the total number of GPUs we have
            args.batch_size = int(args.batch_size / ngpus_per_node)
            args.workers = int((args.workers + ngpus_per_node - 1) / ngpus_per_node)
            model = torch.nn.parallel.DistributedDataParallel(
                model, device_ids=[args.gpu]
            )
        else:
            model.cuda()
            # DistributedDataParallel will divide and allocate batch_size to all
            # available GPUs if device_ids are not set
            model = torch.nn.parallel.DistributedDataParallel(model)
    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
        model = torch.nn.DataParallel(model).cuda()

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

    # Data loading code
    valdir = os.path.join(args.data, "val")

    val_loader = torch.utils.data.DataLoader(
        datasets.ImageFolder(
            valdir,
            transforms.Compose(
                [
                    transforms.Resize(
                        args.resolution,
                        interpolation=transforms.InterpolationMode.BICUBIC,
                    ),
                    transforms.CenterCrop(args.resolution),
                    transforms.ToTensor(),
                    transforms.Normalize(
                        mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]
                    ),
                ]
            ),
        ),
        batch_size=args.batch_size,
        shuffle=False,
        num_workers=args.workers,
        pin_memory=True,
    )

    validate(val_loader, model, criterion, args)


def validate(val_loader, model, criterion, args):
    batch_time = AverageMeter("Time", ":6.3f", Summary.NONE)
    losses = AverageMeter("Loss", ":.4e", Summary.NONE)
    top1 = AverageMeter("Acc@1", ":6.2f", Summary.AVERAGE)
    top5 = AverageMeter("Acc@5", ":6.2f", Summary.AVERAGE)
    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)

        progress.display_summary()

    return top1.avg


class Summary(Enum):
    NONE = 0
    AVERAGE = 1
    SUM = 2
    COUNT = 3


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

    def __init__(self, name, fmt=":f", summary_type=Summary.AVERAGE):
        self.name = name
        self.fmt = fmt
        self.summary_type = summary_type
        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__)

    def summary(self):
        fmtstr = ""
        if self.summary_type is Summary.NONE:
            fmtstr = ""
        elif self.summary_type is Summary.AVERAGE:
            fmtstr = "{name} {avg:.3f}"
        elif self.summary_type is Summary.SUM:
            fmtstr = "{name} {sum:.3f}"
        elif self.summary_type is Summary.COUNT:
            fmtstr = "{name} {count:.3f}"
        else:
            raise ValueError("invalid summary type %r" % self.summary_type)

        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 display_summary(self):
        entries = [" *"]
        entries += [meter.summary() for meter in self.meters]
        print(" ".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 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()