Adding Repeated Augment Sampler (#5051)

* Adding repaeted data-augument sampler

* rebase on top of latest main

* fix formatting

* rename file

* adding coode source

references/classification/sampler.py

+import math
+
+import torch
+import torch.distributed as dist
+
+
+class RASampler(torch.utils.data.Sampler):
+    """Sampler that restricts data loading to a subset of the dataset for distributed,
+    with repeated augmentation.
+    It ensures that different each augmented version of a sample will be visible to a
+    different process (GPU).
+    Heavily based on 'torch.utils.data.DistributedSampler'.
+
+    This is borrowed from the DeiT Repo:
+    https://github.com/facebookresearch/deit/blob/main/samplers.py
+    """
+
+    def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True):
+        if num_replicas is None:
+            if not dist.is_available():
+                raise RuntimeError("Requires distributed package to be available!")
+            num_replicas = dist.get_world_size()
+        if rank is None:
+            if not dist.is_available():
+                raise RuntimeError("Requires distributed package to be available!")
+            rank = dist.get_rank()
+        self.dataset = dataset
+        self.num_replicas = num_replicas
+        self.rank = rank
+        self.epoch = 0
+        self.num_samples = int(math.ceil(len(self.dataset) * 3.0 / self.num_replicas))
+        self.total_size = self.num_samples * self.num_replicas
+        self.num_selected_samples = int(math.floor(len(self.dataset) // 256 * 256 / self.num_replicas))
+        self.shuffle = shuffle
+
+    def __iter__(self):
+        # Deterministically shuffle based on epoch
+        g = torch.Generator()
+        g.manual_seed(self.epoch)
+        if self.shuffle:
+            indices = torch.randperm(len(self.dataset), generator=g).tolist()
+        else:
+            indices = list(range(len(self.dataset)))
+
+        # Add extra samples to make it evenly divisible
+        indices = [ele for ele in indices for i in range(3)]
+        indices += indices[: (self.total_size - len(indices))]
+        assert len(indices) == self.total_size
+
+        # Subsample
+        indices = indices[self.rank : self.total_size : self.num_replicas]
+        assert len(indices) == self.num_samples
+
+        return iter(indices[: self.num_selected_samples])
+
+    def __len__(self):
+        return self.num_selected_samples
+
+    def set_epoch(self, epoch):
+        self.epoch = epoch

references/classification/train.py

@@ -9,6 +9,7 @@ import torch.utils.data
 import torchvision
 import transforms
 import utils
+from references.classification.sampler import RASampler
 from torch import nn
 from torch.utils.data.dataloader import default_collate
 from torchvision.transforms.functional import InterpolationMode
@@ -172,6 +173,9 @@ def load_data(traindir, valdir, args):
 
     print("Creating data loaders")
     if args.distributed:
+        if args.ra_sampler:
+            train_sampler = RASampler(dataset, shuffle=True)
+        else:
             train_sampler = torch.utils.data.distributed.DistributedSampler(dataset)
         test_sampler = torch.utils.data.distributed.DistributedSampler(dataset_test, shuffle=False)
     else:
@@ -481,6 +485,7 @@ def get_args_parser(add_help=True):
         "--train-crop-size", default=224, type=int, help="the random crop size used for training (default: 224)"
     )
     parser.add_argument("--clip-grad-norm", default=None, type=float, help="the maximum gradient norm (default None)")
+    parser.add_argument("--ra-sampler", action="store_true", help="whether to use ra_sampler in training")
 
     # Prototype models only
     parser.add_argument("--weights", default=None, type=str, help="the weights enum name to load")