dataloader.py 文件源码

def __init__(self, loader):
        self.dataset = loader.dataset
        self.collate_fn = loader.collate_fn
        self.batch_sampler = loader.batch_sampler
        self.num_workers = loader.num_workers
        self.pin_memory = loader.pin_memory and torch.cuda.is_available()
        self.timeout = loader.timeout
        self.done_event = threading.Event()

        self.sample_iter = iter(self.batch_sampler)

        if self.num_workers > 0:
            self.worker_init_fn = loader.worker_init_fn
            self.index_queue = multiprocessing.SimpleQueue()
            self.worker_result_queue = multiprocessing.SimpleQueue()
            self.batches_outstanding = 0
            self.worker_pids_set = False
            self.shutdown = False
            self.send_idx = 0
            self.rcvd_idx = 0
            self.reorder_dict = {}

            base_seed = torch.LongTensor(1).random_()[0]
            self.workers = [
                multiprocessing.Process(
                    target=_worker_loop,
                    args=(self.dataset, self.index_queue, self.worker_result_queue, self.collate_fn,
                          base_seed + i, self.worker_init_fn, i))
                for i in range(self.num_workers)]

            if self.pin_memory or self.timeout > 0:
                self.data_queue = queue.Queue()
                self.worker_manager_thread = threading.Thread(
                    target=_worker_manager_loop,
                    args=(self.worker_result_queue, self.data_queue, self.done_event, self.pin_memory,
                          torch.cuda.current_device()))
                self.worker_manager_thread.daemon = True
                self.worker_manager_thread.start()
            else:
                self.data_queue = self.worker_result_queue

            for w in self.workers:
                w.daemon = True  # ensure that the worker exits on process exit
                w.start()

            _update_worker_pids(id(self), tuple(w.pid for w in self.workers))
            _set_SIGCHLD_handler()
            self.worker_pids_set = True

            # prime the prefetch loop
            for _ in range(2 * self.num_workers):
                self._put_indices()