fit_generator是否需要神经网络所有层的输入?

时间:2020-01-24 15:56:01

标签: python keras

对Keras有所了解,并构建了具有两个密集层的神经网络。内存中存储的数据太多,因此我正在使用fit_generator函数,但收到错误ValueError: No data provided for "dense_2". Need data for each key in: ['dense_2']。下面的小例子:

from keras.models import Sequential
from keras.layers import Dense
import numpy as np

model = Sequential([
    Dense(100, input_shape=(1924800,), activation='relu'),
    Dense(1, activation='sigmoid')
])

model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])

def generate_arrays_from_files(path, batch_size=50):
    while True:
        # Do things....
        yield ({'dense_1_input': np.asarray(outdata)}, {'output': np.asarray(outlabels)})

model.fit_generator(generate_arrays_from_files(path), steps_per_epoch=5, epochs=10)

编辑:忘记了编译行

1 个答案:

答案 0 :(得分:0)

您不需要在输入中指定层,并且显然不需要将数据传递到第二个密集层。请注意,最好使用Keras生成器,您可以创建一个自定义生成器,例如thisuse a standard one

您还需要编译模型。

from keras.models import Sequential
from keras.layers import Dense
import numpy as np

model = Sequential([
    Dense(100, input_shape=(1924800,), activation='relu'),
    Dense(1, activation='sigmoid')
])

optimizer = keras.optimizers.Adam(lr=1e-3)
model.compile(loss='binary_crossentropy',
              optimizer=optimizer,
              metrics=['accuracy'])

def generate_arrays_from_files(path, batch_size=50):
    while True:
        # Do things....
        yield np.asarray(outdata), np.asarray(outlabels)

model.fit_generator(generate_arrays_from_files(path), steps_per_epoch=5, epochs=10)

顺便将(1924800,)的向量馈送到模型是否正常?