Keras网络拟合:损失是“难"，准确性不会改变 [英] Keras network fit: loss is 'nan', accuracy doesn't change

问题描述

我尝试拟合keras网络，但是在每个时期中损失都是'nan'，准确性也不会改变...我试图更改时期，层数，神经元数，学习率，优化器，我检查了nan数据.数据集，通过不同的方式对数据进行归一化，但问题仍未解决.感谢您的帮助.

I try to fit keras network, but in each epoch loss is 'nan' and accuracy doesn't change... I tried to change epoch, layers count, neurons count, learning rate, optimizers, I checked nan data in datasets, normalize data by different ways, but problem was not solved. Thanks for your help.

np.random.seed(1337)

# example of input vector: [-1.459746, 0.2694708, ... 0.90043]
# example of output vector: [1, 0] or [0, 1]

model = Sequential()
model.add(Dense(1000, activation='tanh', init='normal', input_dim=503))
model.add(Dense(2, init='normal', activation='softmax'))

opt = optimizers.sgd(lr=0.01)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=['accuracy'])

print(model.summary())

model.fit(x_train, y_train, batch_size=1000, nb_epoch=100, verbose=1)

99804/99804 [==============================] - 5s 52us/step - loss: nan - acc: 0.4938
Epoch 1/100
99804/99804 [==============================] - 5s 49us/step - loss: nan - acc: 0.4938
Epoch 2/100
99804/99804 [==============================] - 5s 51us/step - loss: nan - acc: 0.4938
Epoch 3/100
99804/99804 [==============================] - 5s 52us/step - loss: nan - acc: 0.4938
Epoch 4/100
99804/99804 [==============================] - 5s 52us/step - loss: nan - acc: 0.4938
Epoch 5/100
99804/99804 [==============================] - 5s 51us/step - loss: nan - acc: 0.4938
...

推荐答案

哦，发现问题了！归一化后，在输入向量中出现了一个神经元.

Oh, problem has been found! After normalization, one nan neuron appeared in the input vector

这篇关于Keras网络拟合:损失是“难"，准确性不会改变的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！