From 495ffc4777522e40941753e3b1b79c02f84b25b4 Mon Sep 17 00:00:00 2001
From: Grafting Rayman <156515434+GraftingRayman@users.noreply.github.com>
Date: Fri, 17 Jan 2025 11:00:30 +0000
Subject: Add files via upload

---
 r_basicsr/data/data_sampler.py | 48 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 r_basicsr/data/data_sampler.py

(limited to 'r_basicsr/data/data_sampler.py')

diff --git a/r_basicsr/data/data_sampler.py b/r_basicsr/data/data_sampler.py
new file mode 100644
index 0000000..5135c7f
--- /dev/null
+++ b/r_basicsr/data/data_sampler.py
@@ -0,0 +1,48 @@
+import math
+import torch
+from torch.utils.data.sampler import Sampler
+
+
+class EnlargedSampler(Sampler):
+    """Sampler that restricts data loading to a subset of the dataset.
+
+    Modified from torch.utils.data.distributed.DistributedSampler
+    Support enlarging the dataset for iteration-based training, for saving
+    time when restart the dataloader after each epoch
+
+    Args:
+        dataset (torch.utils.data.Dataset): Dataset used for sampling.
+        num_replicas (int | None): Number of processes participating in
+            the training. It is usually the world_size.
+        rank (int | None): Rank of the current process within num_replicas.
+        ratio (int): Enlarging ratio. Default: 1.
+    """
+
+    def __init__(self, dataset, num_replicas, rank, ratio=1):
+        self.dataset = dataset
+        self.num_replicas = num_replicas
+        self.rank = rank
+        self.epoch = 0
+        self.num_samples = math.ceil(len(self.dataset) * ratio / self.num_replicas)
+        self.total_size = self.num_samples * self.num_replicas
+
+    def __iter__(self):
+        # deterministically shuffle based on epoch
+        g = torch.Generator()
+        g.manual_seed(self.epoch)
+        indices = torch.randperm(self.total_size, generator=g).tolist()
+
+        dataset_size = len(self.dataset)
+        indices = [v % dataset_size for v in indices]
+
+        # subsample
+        indices = indices[self.rank:self.total_size:self.num_replicas]
+        assert len(indices) == self.num_samples
+
+        return iter(indices)
+
+    def __len__(self):
+        return self.num_samples
+
+    def set_epoch(self, epoch):
+        self.epoch = epoch
-- 
cgit v1.2.3