Created by: yanggb

环境：win10+python3.7 object_detection和face_detection都存在这个错误。哪位朋友帮帮忙，无论是使用推荐数据还是自己的图片数据都报错

参数配置： add_arg('learning_rate', float, 0.001, "Learning rate.") add_arg('batch_size', int, 64, "Minibatch size of all devices.") add_arg('epoc_num', int, 120, "Epoch number.") add_arg('use_gpu', bool, False, "Whether use GPU.") add_arg('parallel', bool, False, "Whether train in parallel on multi-devices.") add_arg('dataset', str, 'pascalvoc', "dataset can be coco2014, coco2017, and pascalvoc.") add_arg('model_save_dir', str, 'model', "The path to save model.") add_arg('pretrained_model', str, 'pretrained/ssd_mobilenet_v1_coco/', "The init model path.") add_arg('ap_version', str, '11point', "mAP version can be integral or 11point.") add_arg('image_shape', str, '3,300,300', "Input image shape.") add_arg('mean_BGR', str, '127.5,127.5,127.5', "Mean value for B,G,R channel which will be subtracted.") add_arg('data_dir', str, 'data/pascalvoc', "Data directory.") add_arg('enable_ce', bool, True, "Whether use CE to evaluate the model.")

报错log: Exception in thread Thread-3: Traceback (most recent call last): File "G:\Python36\lib\threading.py", line 916, in _bootstrap_inner self.run() File "G:\Python36\lib\threading.py", line 864, in run self._target(*self._args, **self._kwargs) File "G:\Python36\lib\site-packages\paddle\fluid\layers\io.py", line 585, in provider_thread raise ex File "G:\Python36\lib\site-packages\paddle\fluid\layers\io.py", line 567, in provider_thread for tensors in func(): File "G:\Python36\lib\site-packages\paddle\fluid\layers\io.py", line 617, in tensor_provider for slots in paddle_reader(): File "G:\Python36\lib\site-packages\paddle\fluid\data_feeder.py", line 326, in reader_creator for item in reader(): File "G:\Python36\lib\site-packages\paddle\reader\decorator.py", line 404, in queue_reader p.start() File "G:\Python36\lib\multiprocessing\process.py", line 105, in start self._popen = self._Popen(self) File "G:\Python36\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "G:\Python36\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "G:\Python36\lib\multiprocessing\popen_spawn_win32.py", line 65, in init reduction.dump(process_obj, to_child) File "G:\Python36\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) AttributeError: Can't pickle local object 'multiprocess_reader.._read_into_queue'

Traceback (most recent call last): File "", line 1, in File "G:\Python36\lib\multiprocessing\spawn.py", line 105, in spawn_main exitcode = _main(fd) File "G:\Python36\lib\multiprocessing\spawn.py", line 115, in _main self = reduction.pickle.load(from_parent) EOFError: Ran out of input