AAAI Version

AAAI Supplementary Material/Model Training Code/data/samplers.py

@@ -0,0 +1,73 @@
+# Repeat Augment sampler taken from DeiT: https://github.com/facebookresearch/deit/blob/main/samplers.py
+# Copyright (c) 2015-present, Facebook, Inc.
+# All rights reserved.
+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
+    """
+
+    def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True, num_repeats: int = 3):
+        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()
+        if num_repeats < 1:
+            raise ValueError("num_repeats should be greater than 0")
+        self.dataset = dataset
+        self.num_replicas = num_replicas
+        self.rank = rank
+        self.num_repeats = num_repeats
+        self.epoch = 0
+        self.num_samples = int(math.ceil(len(self.dataset) * self.num_repeats / self.num_replicas))
+        self.total_size = self.num_samples * self.num_replicas
+        # self.num_selected_samples = int(math.ceil(len(self.dataset) / self.num_replicas))
+        self.num_selected_samples = int(math.floor(len(self.dataset) // 256 * 256 / self.num_replicas))
+        self.shuffle = shuffle
+
+    def __iter__(self):
+        if self.shuffle:
+            # deterministically shuffle based on epoch
+            g = torch.Generator()
+            g.manual_seed(self.epoch)
+            indices = torch.randperm(len(self.dataset), generator=g)
+        else:
+            indices = torch.arange(start=0, end=len(self.dataset))
+
+        # add extra samples to make it evenly divisible
+        indices = torch.repeat_interleave(indices, repeats=self.num_repeats, dim=0).tolist()
+        padding_size: int = self.total_size - len(indices)
+        if padding_size > 0:
+            indices += indices[:padding_size]
+        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
+
+    def __str__(self) -> str:
+        return (
+            f"{type(self).__name__}(num_replicas: {self.num_replicas}, rank: {self.rank}, num_repeats:"
+            f" {self.num_repeats}, epoch: {self.epoch}, num_samples: {self.num_samples}, total_size: {self.total_size},"
+            f" num_selected_samples: {self.num_selected_samples}, shuffle: {self.shuffle})"
+        )