python keras neural network: IndexError: indices are out-of-bounds

Question

我试图为多类分类拟合神经网络模型，但我有

IndexError: indices are out-of-bounds

错误。我的训练数据的维度是 (26728, 450)，有 450 个特征。输出大小为 5 (5 类)。我使用 to_categorical(train_Y) 将其转换为 5 列矩阵。

密码是

model = Sequential()

model.add(Dense(64, input_dim=train_X.shape[1], init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(64, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(5, init='uniform'))
model.add(Activation('softmax'))

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

train_Y_keras = to_categorical(train_Y)
model.fit(train_X, train_Y_keras, nb_epoch=10)

层的添加我不是很明白，我复制并修改了这里给出的代码http://keras.io/getting-started/functional-api-guide/#getting-started-with-the-keras-functional-api，谁能指出我的错误？谢谢。

Answer 1

我通过将 pandas 数据帧转换为 numpy 数组使其工作。

python keras neural network: IndexError: indices are out-of-bounds

python keras neural network: IndexError: indices are out-of-bounds

python

neural-network

training-data

keras