Tensorflow:cifar10.py或cifar10_input.py不工作

Tensorflow:cifar10.py或cifar10_input.py不工作,tensorflow,Tensorflow,如果我尝试在cifar10\u train.py文件中使用cifar10.py和cifar10\u input.py, 它给出了以下错误: Filling queue with 20000 CIFAR images before starting to train. This will take a few minutes. I tensorflow/core/common_runtime/local_device.cc:25] Local device intra op parallelis

如果我尝试在cifar10\u train.py文件中使用cifar10.py和cifar10\u input.py, 它给出了以下错误:

Filling queue with 20000 CIFAR images before starting to train. This will take a few minutes.

I tensorflow/core/common_runtime/local_device.cc:25] Local device intra op parallelism threads: 4

I tensorflow/core/common_runtime/local_session.cc:45] Local session inter op parallelism threads: 4

W tensorflow/core/kernels/queue_ops.cc:114] Invalid argument: Signature mismatch, have: string_ref, float-> expected: string_ref, string->
然后终端挂起

我只改变了两件事:

  • 我将“从tensorflow.models.image.cifar10导入cifar10”替换为“导入cifar10”,对于cifar10\u input.py也是如此

  • 将max_steps设置为5000,以检查代码是否运行正常

  • 任何帮助都将不胜感激。谢谢

    解决了这个问题

    至少应有2个输入(.bin)文件。我以前试过一个文件。例如,应该有数据批处理1.bin和数据批处理2.bin。我以前试过使用data\u batch\u 1.bin