dataloader.py 文件源码

def __init__(self, loader):
        self.dataset = loader.dataset
        self.batch_size = loader.batch_size
        self.collate_fn = loader.collate_fn
        self.sampler = loader.sampler
        self.num_workers = loader.num_workers
        self.pin_memory = loader.pin_memory
        self.done_event = threading.Event()

        self.samples_remaining = len(self.sampler)
        self.sample_iter = iter(self.sampler)

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

            self.workers = [
                multiprocessing.Process(
                    target=_worker_loop,
                    args=(self.dataset, self.index_queue, self.data_queue, self.collate_fn))
                for _ in range(self.num_workers)]

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

            if self.pin_memory:
                in_data = self.data_queue
                self.data_queue = queue.Queue()
                self.pin_thread = threading.Thread(
                    target=_pin_memory_loop,
                    args=(in_data, self.data_queue, self.done_event))
                self.pin_thread.daemon = True
                self.pin_thread.start()

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