Download examples/image-classification/sampler.py from UniversalAlgorithmic/SPG: direct link, hf CLI and curl.
- Browser
- Download file 2.4 kB
-
https://huggingface.co/UniversalAlgorithmic/SPG/resolve/main/examples/image-classification/sampler.py
- Command line
-
hf download hf://UniversalAlgorithmic/SPG/examples/image-classification/sampler.py
-
curl -L -o sampler.py https://huggingface.co/UniversalAlgorithmic/SPG/resolve/main/examples/image-classification/sampler.py
2.4 kB
| 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, seed=0, repetitions=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() | |
| self.dataset = dataset | |
| self.num_replicas = num_replicas | |
| self.rank = rank | |
| self.epoch = 0 | |
| self.num_samples = int(math.ceil(len(self.dataset) * float(repetitions) / 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 | |
| self.seed = seed | |
| self.repetitions = repetitions | |
| def __iter__(self): | |
| if self.shuffle: | |
| # Deterministically shuffle based on epoch | |
| g = torch.Generator() | |
| g.manual_seed(self.seed + self.epoch) | |
| 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(self.repetitions)] | |
| 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 | |