i3ddlZddlmZddlmZddlZddlmZddl m Z ddl m Z dgZ edd ZGd de eZy) N)Iterator)TypeVar)Dataset)SamplerDistributedSampler_T_coT) covariantczeZdZdZ ddededzdedzdededed dfd Zd ee fd Z d efd Z d ed dfdZ y)ra' Sampler that restricts data loading to a subset of the dataset. It is especially useful in conjunction with :class:`torch.nn.parallel.DistributedDataParallel`. In such a case, each process can pass a :class:`~torch.utils.data.DistributedSampler` instance as a :class:`~torch.utils.data.DataLoader` sampler, and load a subset of the original dataset that is exclusive to it. .. note:: Dataset is assumed to be of constant size and that any instance of it always returns the same elements in the same order. Args: dataset: Dataset used for sampling. num_replicas (int, optional): Number of processes participating in distributed training. By default, :attr:`world_size` is retrieved from the current distributed group. rank (int, optional): Rank of the current process within :attr:`num_replicas`. By default, :attr:`rank` is retrieved from the current distributed group. shuffle (bool, optional): If ``True`` (default), sampler will shuffle the indices. seed (int, optional): random seed used to shuffle the sampler if :attr:`shuffle=True`. This number should be identical across all processes in the distributed group. Default: ``0``. drop_last (bool, optional): if ``True``, then the sampler will drop the tail of the data to make it evenly divisible across the number of replicas. If ``False``, the sampler will add extra indices to make the data evenly divisible across the replicas. Default: ``False``. .. warning:: In distributed mode, calling the :meth:`set_epoch` method at the beginning of each epoch **before** creating the :class:`DataLoader` iterator is necessary to make shuffling work properly across multiple epochs. Otherwise, the same ordering will be always used. Example:: >>> # xdoctest: +SKIP >>> sampler = DistributedSampler(dataset) if is_distributed else None >>> loader = DataLoader(dataset, shuffle=(sampler is None), ... sampler=sampler) >>> for epoch in range(start_epoch, n_epochs): ... if is_distributed: ... sampler.set_epoch(epoch) ... train(loader) Ndataset num_replicasrankshuffleseed drop_lastreturnc|3tjs tdtj}|3tjs tdtj}||k\s|dkrt d|d|dz d||_||_||_d|_ ||_ |jrmt|j |jzdk7rHtjt|j |jz |jz |_n:tjt|j |jz |_|j|jz|_||_||_y)Nz,Requires distributed package to be availablerz Invalid rank z%, rank should be in the interval [0, ])dist is_available RuntimeErrorget_world_sizeget_rank ValueErrorr r r epochrlenmathceil num_samples total_sizerr)selfr r r rrrs q/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torch/utils/data/distributed.py__init__zDistributedSampler.__init__BsZ  $$&"#QRR..0L <$$&"#QRR==?D < 4!8v%J>c$,,/$2C2CCqH $yyT\\"T%6%66$:K:KK D  $yyT\\):T=N=N)NOD **T->->>  c|jrutj}|j|j|j ztj t|j|j}n'ttt|j}|jsZ|jt|z }|t|kr ||d|z }n:||tj|t|z zd|z }n|d|j}t||jk7r%t!dt|d|jd||j"|j|j$}t||j&k7r%t!dt|d|j&dt)|S)N) generatorzNumber of indices (z) does not match total_size ()zNumber of subsampled indices (z) does not match num_samples ()rtorch Generator manual_seedrrrandpermrr tolistlistrangerr rrAssertionErrorr r riter)r!gindices padding_sizes r"__iter__zDistributedSampler.__iter__ks <<!A MM$))djj0 1nnS%6!DKKMG5T\\!234G~~??S\9Ls7|+7=L11Gdii s7|0K&LL!\ /0G w<4?? * %c'l^3PQUQ`Q`Paabc  $))doo8I8IIJ w<4++ + 0W>\]a]m]m\nnop  G}r$c|jS)N)r)r!s r"__len__zDistributedSampler.__len__sr$rc||_y)a1 Set the epoch for this sampler. When :attr:`shuffle=True`, this ensures all replicas use a different random ordering for each epoch. Otherwise, the next iteration of this sampler will yield the same ordering. Args: epoch (int): Epoch number. N)r)r!rs r" set_epochzDistributedSampler.set_epochs  r$)NNTrF) __name__ __module__ __qualname____doc__rintboolr#rrr4r6r8r$r"rrs.f$(''Dj'Dj '  '  '' 'R"(5/"H   s t r$)rcollections.abcrtypingrr(torch.distributed distributedrtorch.utils.data.datasetrtorch.utils.data.samplerr__all__rrr?r$r"rGsD $ ,,  4(LLr$