tensorflow - 使用 keras 和 tensorflow "You must feed a value for placeholder tensor ' input_ 1' with dtype float"

Question

我在训练 GAN 的判别器时收到意外错误“您必须为占位符张量‘input_1’提供一个值，其中包含 dtype float”

错误在这里:

W tensorflow/core/framework/op_kernel.cc:975] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
     [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
W tensorflow/core/framework/op_kernel.cc:975] Invalid argument: You must feed a value for placeholder tensor 'input_1' with dtype float
     [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
Traceback (most recent call last):
  File "new_model.py", line 204, in <module>
    main()
  File "new_model.py", line 201, in main
    train(nb_epoch=10, BATCH_SIZE=5)
  File "new_model.py", line 176, in train
    d_loss = discriminator.train_on_batch(image_to_dis, label_to_dis)            
  File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 766, in train_on_batch
    class_weight=class_weight)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1320, in train_on_batch
    outputs = self.train_function(ins)
  File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 1943, in __call__
    feed_dict=feed_dict)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 766, in run
    run_metadata_ptr)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 964, in _run
    feed_dict_string, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1014, in _do_run
    target_list, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1034, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'input_1' with dtype float
     [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
     [[Node: moments_4/sufficient_statistics/Shape/_217 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_1267_moments_4/sufficient_statistics/Shape", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Caused by op u'input_1', defined at:
  File "new_model.py", line 204, in <module>
    main()
  File "new_model.py", line 201, in main
    train(nb_epoch=10, BATCH_SIZE=5)
  File "new_model.py", line 134, in train
    transformer0 = transform_model()
  File "new_model.py", line 22, in transform_model
    inputs = Input(shape=( 128, 128, 3))
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 1198, in Input
    input_tensor=tensor)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 1116, in __init__
    name=self.name)
  File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 321, in placeholder
    x = tf.placeholder(dtype, shape=shape, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 1587, in placeholder
    name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 2043, in _placeholder
    name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2240, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1128, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'input_1' with dtype float
     [[Node: input_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
     [[Node: moments_4/sufficient_statistics/Shape/_217 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_1267_moments_4/sufficient_statistics/Shape", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

似乎错误发生在

d_loss = discriminator.train_on_batch(image_to_dis, label_to_dis)

我确定 image_to_dis 和 label_to_dis 适合判别器的输入然而，这里的错误信息

Caused by op u'input_1', defined at:
  File "new_model.py", line 204, in <module>
    main()
  File "new_model.py", line 201, in main
    train(nb_epoch=10, BATCH_SIZE=5)
  File "new_model.py", line 134, in train
    transformer0 = transform_model()
  File "new_model.py", line 22, in transform_model
    inputs = Input(shape=( 128, 128, 3))

它说错误是由'transformer'(它是这个GAN中的生成器)的输入张量引起的。

我的代码包含类似“transformer_with_discriminator = discriminator(transformer)”的内容，但鉴别器是在没有转换器的情况下编译的。我认为训练鉴别器与'transformer0'的输入无关

整个脚本有点长，可以把我模型的链接放在这里吗？

https://github.com/wkcw/keras-face-attribute/blob/master/model%26train.py

image_to_dis.dtype 和 label_to_dis.dtype 都是 float32，我试过将 label_to_dis.dtype 转换为 int

我真的不知道这个......

Answer 1

它来自批归一化。你可以在这里看到:https://stackoverflow.com/a/42470757/7137636如何解决这个问题。

如果您需要更多信息，请在评论中询问 :)