我试图在 jupyter notebook 中的 mnist 数据集上运行以下代码,但出现以下错误。我发现已经发布了类似的问题,但无法使用给定的信息解决错误。任何线索都会有所帮助。谢谢!
错误: ValueError: 没有为任何变量提供梯度:['dense/kernel:0', 'dense/bias:0', 'dense_1/kernel:0', 'dense_1/bias:0', 'dense_2/kernel:0', 'dense_2/bias:0']。
from keras.datasets import mnist
data=mnist.load_data()
type(data)
(X_train, y_train), (X_test, y_test) = data
X_train[0].shape
X_train.shape
X_test.shape
type(X_train)
import cv2
type(X_train[0])
cv2.startWindowThread()
cv2.namedWindow("preview")
cv2.imshow('ImageWindow',X_train[0])
cv2.waitKey()
X_train=X_train.reshape(X_train.shape[0],28*28).astype('float32')
X_test=X_test.reshape(X_test.shape[0],28*28).astype('float32')
X_train=X_train/255
X_test=X_test/255
from keras.models import Sequential
from keras.layers import Dense
model = Sequential()
model.add(Dense(32, input_dim = 28 * 28, activation= 'relu'))
model.add(Dense(64, activation = 'relu'))
model.add(Dense(10, activation = 'softmax'))
model.compile()
model.summary()
model.fit(X_train,y_train,epochs=10,batch_size=100)
在最后一行我收到错误: ValueError: 没有为任何变量提供梯度:['dense/kernel:0', 'dense/bias:0', 'dense_1/kernel:0', 'dense_1/bias:0', 'dense_2/kernel:0', 'dense_2/bias:0']。