调用 Dense 时出现 Keras 问题

Question

我一直试图在下面运行这段代码，但它一直抛出一个错误。

这是我试图在 ipython 上运行的代码。谁能告诉我是什么问题？

import numpy as np
import matplotlib.pyplot as plt
from util import getKaggleMNIST
from keras.models import Model
from keras.layers import Dense, Activation, Input

xtrain, ytrain, xtest, ytest = getKaggleMNIST()

N, D = xtrain.shape
k = len(set(ytrain))

i = Input(shape=(D,))
x = Dense(500, activation='relu')(i)
x = Dense(300, activation='relu')(x)
x = Dense(k, activation='softmax')(k)

model = Model(inputs=i, outputs=x)

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

r = model.fit(Xtrain, Ytrain, validation_data=(Xtest, Ytest), epochs=15, batch_size=32)

print("Returned:", r)

plt.plot(r.history['loss'], label='loss') 
plt.plot(r.history['val_loss'], label='val_loss') 
plt.legend() 
plt.show()

这是错误：

ValueError: Layer dense_3 was called with an input that isn't a symbolic tensor. Received type: <type 'int'>. Full input: [10]. All inputs to the layer should be tensors.

先谢谢了。

Answer 1

将x = Dense(k, activation='softmax')(k) 替换为x = Dense(k, activation='softmax')(x)