我不断收到此错误“ValueError：检查输入时出错：预期的dense_8_input有2维，但得到的数组形状为（705,66,1）”

Question

'MLP'

'在训练数据集上定义和拟合 model'

def fit_model(trainX, trainy, testX, testy):
    'define model'
    model = Sequential()
    model.add(Dense(5, input_dim=2, activation='relu', kernel_initializer='he_uniform'))
    model.add(Dense(5, activation='relu', kernel_initializer='he_uniform'))
    model.add(Dense(3, activation='softmax'))
    'compile model'
    model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['acc'])
    'fit model'
    history = model.fit(trainX, trainy, validation_data=(testX, testy), epochs=100, batch_size=66, verbose=0)
    return model, history

# fit model on train dataset
model, history = fit_model(trainX, trainy, testX, testy)
# evaluate model behavior
summarize_model(model, history, trainX, trainy, testX, testy)
# save model to file
model.save('model.h5')

Answer 1

你必须将它们作为列表传递，你不能有 4 个不同的 arguments

def fit_model(train, test):

像这样打电话给 fit

fit_model([trainX, trainy], [testX, testy], batch_size=16, epochs=100)