テンソルがわかりません

Question

MNISTを使った機械学習のプログラムをFunction APIを使って書こうと思ったのですがうまくできません。入力はテンソルでないといけないということなのですが、そもそもテンソルについてよくわかりませんでした。どこに問題があるか教えていだだけますでしょうか。

Traceback (most recent call last):
  File "/Users/nakagamiyuta/.pyenv/versions/3.7.4/lib/python3.7/site-packages/keras/engine/base_layer.py", line 310, in assert_input_compatibility
    K.is_keras_tensor(x)
  File "/Users/nakagamiyuta/.pyenv/versions/3.7.4/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py", line 697, in is_keras_tensor
    str(type(x)) + '`. '
ValueError: Unexpectedly found an instance of type `<class 'keras.engine.input_layer.InputLayer'>`. Expected a symbolic tensor instance.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "Function.py", line 32, in <module>
    x=Dense(128, activation='relu')(inputs) 
  File "/Users/nakagamiyuta/.pyenv/versions/3.7.4/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py", line 75, in symbolic_fn_wrapper
    return func(*args, **kwargs)
  File "/Users/nakagamiyuta/.pyenv/versions/3.7.4/lib/python3.7/site-packages/keras/engine/base_layer.py", line 446, in __call__
    self.assert_input_compatibility(inputs)
  File "/Users/nakagamiyuta/.pyenv/versions/3.7.4/lib/python3.7/site-packages/keras/engine/base_layer.py", line 316, in assert_input_compatibility
    str(inputs) + '. All inputs to the layer '
ValueError: Layer dense_1 was called with an input that isn't a symbolic tensor. Received type: <class 'keras.engine.input_layer.InputLayer'>. Full input: [<keras.engine.input_layer.InputLayer object at 0x14dc8d050>]. All inputs to the layer should be tensors.

書いたコードはこちらです。

import tensorflow as tf
import keras			
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, InputLayer
from keras.optimizers import RMSprop

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

x_train  = x_train.reshape(60000, 784)	
x_test   = x_test.reshape(10000, 784)	

x_train  = x_train.astype('float32')
x_test   = x_test.astype('float32')


x_train /= 255
x_test  /= 255

y_train  = keras.utils.to_categorical(y_train, 10)
y_test   = keras.utils.to_categorical(y_test, 10)

inputs = InputLayer(input_shape=(784,))

x=Dense(128, activation='relu')(inputs) 
x=Dropout(0.2)(x)

predictions=Dense(10, activation='softmax')(x)

model=keras.Model(inputs=inputs,outputs=predictions)


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


epochs = 8	
batch_size = 1024

history = model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(x_test, y_test))

score = model.evaluate(x_test, y_test, verbose=1)
print()
print('Test loss:', score[0])
print('Test accuracy:', score[1])

Answer 1

from keras.layers import Dense, Dropout, InputLayer
↓
from keras.layers import Dense, Dropout, Input

inputs = InputLayer(input_shape=(784,))
↓
inputs = Input(shape=(784,))

ですね。

Comments

[iPatch]

できました。ありがとうございます。
もう一度自分でしっかり調べてみます。