AttributeError：“顺序”对象没有属性“ _feed_input_names”

Question

我正在使用Python 2.7.5跟踪tf.keras tutorial，但是model.fit(data, labels, epochs=10, batch_size=32)给了我错误消息：

>>> model.fit(data, labels, epochs=10, batch_size=32,validation_data=    (val_data, val_labels))

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/software/TensorFlow/1.8-GPU-py2/lib/python2.7/site-packages/tensorflow/python/keras/_impl/keras/engine/training.py", line 1143, in fit
    batch_size=batch_size)
  File "/software/TensorFlow/1.8-GPU-py2/lib/python2.7/site-packages/tensorflow/python/keras/_impl/keras/engine/training.py", line 751, in _standardize_user_data
    feed_input_names = self._feed_input_names
AttributeError: 'Sequential' object has no attribute '_feed_input_names'

谁能指出出什么问题了？

Answer 1

我遇到了同样的问题，不知道为什么，我没有搜索它，但是当我添加了这种浮石时   input_shape =（高度，宽度，通道）到我的第一层网络，错误消失了。

model = keras.models.Sequential()
model.add(firstLayer(....., input_shape=(height,width,channels))

我希望它也会对您有帮助。