Aws lambda 如何在没有管道的情况下运行变压器？

我发现自己正在处理一个不支持多处理的环境。没有变压器管道，我如何运行蒸馏器

下面是当前的代码：

{
  "errorMessage": "[Errno 38] Function not implemented",
  "errorType": "OSError",
  "stackTrace": [
    "  File \"/var/task/lambda_function.py\", line 18, in lambda_handler\n    X = nlp_qa(context=context, question=question)\n",
    "  File \"/mnt/access/transformers/pipelines.py\", line 1776, in __call__\n    features_list = [\n",
    "  File \"/mnt/access/transformers/pipelines.py\", line 1777, in <listcomp>\n    squad_convert_examples_to_features(\n",
    "  File \"/mnt/access/transformers/data/processors/squad.py\", line 354, in squad_convert_examples_to_features\n    with Pool(threads, initializer=squad_convert_example_to_features_init, initargs=(tokenizer,)) as p:\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/context.py\", line 119, in Pool\n    return Pool(processes, initializer, initargs, maxtasksperchild,\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/pool.py\", line 191, in __init__\n    self._setup_queues()\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/pool.py\", line 343, in _setup_queues\n    self._inqueue = self._ctx.SimpleQueue()\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/context.py\", line 113, in SimpleQueue\n    return SimpleQueue(ctx=self.get_context())\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/queues.py\", line 336, in __init__\n    self._rlock = ctx.Lock()\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/context.py\", line 68, in Lock\n    return Lock(ctx=self.get_context())\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/synchronize.py\", line 162, in __init__\n    SemLock.__init__(self, SEMAPHORE, 1, 1, ctx=ctx)\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/synchronize.py\", line 57, in __init__\n    sl = self._semlock = _multiprocessing.SemLock(\n"
  ]
}

导入json
导入操作系统
导入系统
sys.path.append（“/mnt/access”）
进口火炬
从transformers导入AutoTokenizer、AutoModelForQuestionAnswering
从变压器。管道进口管道
def lambda_处理程序（事件、上下文）：
打印（“在：”，os.listdir（“/mnt/access”）之后）
代币器=自动代币器。来自预训练（'/mnt/access/Dis_Save/'））
model=automodelforquestionresponding.from_pretrained（'/mnt/access/Dis_Save/'））
nlp_qa=管道（“问答”，标记器=标记器，模型=模型）
context=“tra”
问题=“tra”
X=nlp_qa（上下文=上下文，问题=问题）
返回{
“状态代码”：200，
'body'：json.dumps（'Hello from Lambda！'）
}

我现在收到的错误消息：

{
  "errorMessage": "[Errno 38] Function not implemented",
  "errorType": "OSError",
  "stackTrace": [
    "  File \"/var/task/lambda_function.py\", line 18, in lambda_handler\n    X = nlp_qa(context=context, question=question)\n",
    "  File \"/mnt/access/transformers/pipelines.py\", line 1776, in __call__\n    features_list = [\n",
    "  File \"/mnt/access/transformers/pipelines.py\", line 1777, in <listcomp>\n    squad_convert_examples_to_features(\n",
    "  File \"/mnt/access/transformers/data/processors/squad.py\", line 354, in squad_convert_examples_to_features\n    with Pool(threads, initializer=squad_convert_example_to_features_init, initargs=(tokenizer,)) as p:\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/context.py\", line 119, in Pool\n    return Pool(processes, initializer, initargs, maxtasksperchild,\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/pool.py\", line 191, in __init__\n    self._setup_queues()\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/pool.py\", line 343, in _setup_queues\n    self._inqueue = self._ctx.SimpleQueue()\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/context.py\", line 113, in SimpleQueue\n    return SimpleQueue(ctx=self.get_context())\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/queues.py\", line 336, in __init__\n    self._rlock = ctx.Lock()\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/context.py\", line 68, in Lock\n    return Lock(ctx=self.get_context())\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/synchronize.py\", line 162, in __init__\n    SemLock.__init__(self, SEMAPHORE, 1, 1, ctx=ctx)\n",
    "  File \"/var/lang/lib/python3.8/multiprocessing/synchronize.py\", line 57, in __init__\n    sl = self._semlock = _multiprocessing.SemLock(\n"
  ]
}

{
“errorMessage”：“[Errno 38]功能未实现”，
“errorType”：“OSError”，
“stackTrace”：[
“文件\“/var/task/lambda_function.py\”，第18行，在lambda_处理程序中\n X=nlp_qa（context=context，question=question）\n“，
“File\”/mnt/access/transformers/pipelines.py\”，第1776行，在调用特性列表=[\n]中，
“File\”/mnt/access/transformers/pipelines.py\”，第1777行，在“班”中将示例转换为特征（\n“，
“File\”/mnt/access/transformers/data/processors/squad.py\”，第354行，在“将示例”转换为“特征”中，将池（线程，初始值设定项=squad\u convert\u示例”转换为“特征”\u init，initargs=（令牌设定项，））作为p:\n“，
“File\”/var/lang/lib/python3.8/multiprocessing/context.py\”，第119行，在池\n返回池中（进程、初始值设定项、initargs、maxtasksperchild，\n“，
“File\”/var/lang/lib/python3.8/multiprocessing/pool.py\”，第191行，在\uuuu init\uuu\n self.\u setup\u queues（）\n中，
“File\”/var/lang/lib/python3.8/multiprocessing/pool.py\”，第343行，在\u setup\u queues\n self.\u inqueue=self.\u ctx.SimpleQueue（）\n中，
“文件\”/var/lang/lib/python3.8/multiprocessing/context.py\”，第113行，在SimpleQueue中\n返回SimpleQueue（ctx=self.get\u context（））\n“，
“File\”/var/lang/lib/python3.8/multiprocessing/queues.py\”，第336行，在\uuuu init\uuun self.\u rlock=ctx.Lock（）\n中，
“文件\”/var/lang/lib/python3.8/multiprocessing/context.py\”，第68行，在Lock\n return Lock（ctx=self.get\u context（））中\n“，
“File\”/var/lang/lib/python3.8/multiprocessing/synchronize.py\”，第162行，在\uuuuu init\uun SemLock.\uuuu init\uuuu（self，信号量，1，1，ctx=ctx）\n中，
文件\“/var/lang/lib/python3.8/multiprocessing/synchronize.py\”，第57行，在\uuuu init\uuu\n sl=self.\u semlock=\u multiprocessing.semlock（\n）
]
}

其他代码：

从transformers导入AutoTokenizer、AutoModelForQuestionAnswering
进口火炬
导入json
导入系统
sys.path.append（“/mnt/access”）
代币器=自动代币器。来自预训练（“/mnt/access/Dis\u Save/”）
model=automodelforquestionresponding.from_pretrained（“/mnt/access/Dis_Save/”，return_dict=True）
def lambda_处理程序（事件、上下文）：
text=r“”
即使在单核环境中，管道也应该工作。如果您收到错误消息，请包括一条错误消息。请查看此消息以获取抽取式问题回答。多处理与Transformers管道有什么关系？@cronoik“errorMessage”：“[Errno 38]函数未实现”，“errorType”：“OSError”，“stackTrace”：[“File\”/var/task/lambda_function.py\”，第18行，在lambda_handler\n X=nlp_qa（context=context，question=question）\n“，@cronoik关于多处理是导致无法工作的原因……AWS支持人员告诉我……这就是我的全部know@cronoik是的，给你。