如何在加载模型时使用Tensorflow / Keras修复python中的'AttributeError：'list'对象没有属性'shape'错误

Question

我试图在Keras中保存我的模型，然后加载它，但是当它尝试使用加载的模型时，抛出错误

Python Vesion：3.6.8 Tensorflow版本：2.0.0-beta1 Keras版本：2.2.4-tf

这是我的代码：

from __future__ import absolute_import, division, print_function, unicode_literals

import tensorflow as tf
from tensorflow import keras

print("Tensorflow Version:")
print(tf.version.VERSION)
print("Keras Verstion:")
print(tf.keras.__version__)

minst = tf.keras.datasets.mnist # 28x28 0-9

(x_train, y_train), (x_test, y_test) = minst.load_data()

x_train = tf.keras.utils.normalize(x_train, axis=1)
x__test = x_test;
x_test = tf.keras.utils.normalize(x_test, axis=1)

model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))
model.add(tf.keras.layers.Dense(10, activation=tf.nn.softmax))

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(x_train, y_train, epochs=1)

val_loss, val_acc = model.evaluate(x_test, y_test)
print(val_loss, val_acc)

model.save('epic_num.h5')
print("Saved")
# Loading

nmodel = keras.models.load_model("epic_num.h5")
import numpy as np;


# Test
predics = nmodel.predict([x_test])
print(predics)

import matplotlib.pyplot as plt

plt.imshow(x__test[11], cmap=plt.cm.binary)
plt.show()

print(np.argmax(predics[11]))

输出：

C:\Users\minec\PycharmProjects\TFMLTest3\venv\Scripts\python.exe C:/Users/minec/PycharmProjects/TFMLTest3/main.py
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
Tensorflow Version:
2.0.0-beta1
Keras Verstion:
2.2.4-tf
2019-08-17 17:02:25.535385: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
WARNING: Logging before flag parsing goes to stderr.
W0817 17:02:25.636994 14512 deprecation.py:323] From C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\ops\math_grad.py:1250: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
Train on 60000 samples

   32/60000 [..............................] - ETA: 2:39 - loss: 2.3092 - accuracy: 0.0938
 1120/60000 [..............................] - ETA: 7s - loss: 1.7317 - accuracy: 0.5580  
...
accuracy: 0.9590
 9600/10000 [===========================>..] - ETA: 0s - loss: 0.1232 - accuracy: 0.9624
10000/10000 [==============================] - 0s 32us/sample - loss: 0.1271 - accuracy: 0.9610
0.1271383908316493 0.961
Saved
W0817 17:02:29.220302 14512 hdf5_format.py:197] Sequential models without an `input_shape` passed to the first layer cannot reload their optimizer state. As a result, your model isstarting with a freshly initialized optimizer.
Traceback (most recent call last):
  File "C:/Users/minec/PycharmProjects/TFMLTest3/main.py", line 41, in <module>
    predics = nmodel.predict([x_test])
  File "C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 821, in predict
    use_multiprocessing=use_multiprocessing)
  File "C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\keras\engine\training_arrays.py", line 705, in predict
    x, check_steps=True, steps_name='steps', steps=steps)
  File "C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 2335, in _standardize_user_data
    self._set_inputs(cast_inputs)
  File "C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 2553, in _set_inputs
    outputs = self(inputs, **kwargs)
  File "C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 662, in __call__
    outputs = call_fn(inputs, *args, **kwargs)
  File "C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\keras\engine\sequential.py", line 262, in call
    outputs = layer(inputs, **kwargs)
  File "C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 662, in __call__
    outputs = call_fn(inputs, *args, **kwargs)
  File "C:\Users\minec\PycharmProjects\TFMLTest3\venv\lib\site-packages\tensorflow\python\keras\layers\core.py", line 580, in call
    inputs, (tensor_shape.dimension_value(inputs.shape[0]) or
AttributeError: 'list' object has no attribute 'shape'

Process finished with exit code 1

Answer 1

尝试使用

nmodel.predict(x_test)

代替

nmodel.predict([x_test])

（卸下支架）。