keras 模型中的平均权重

Question

当我训练具有相同架构和不同初始化的几个模型时，如何平均 Keras 模型中的权重？

现在我的代码看起来像这样？

datagen = ImageDataGenerator(rotation_range=15,
                             width_shift_range=2.0/28,
                             height_shift_range=2.0/28
                            )

epochs = 40 
lr = (1.234e-3)
optimizer = Adam(lr=lr)

main_input = Input(shape= (28,28,1), name='main_input')

sub_models = []

for i in range(5):

    x = Conv2D(32, kernel_size=(3,3), strides=1)(main_input)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = MaxPool2D(pool_size=2)(x)

    x = Conv2D(64, kernel_size=(3,3), strides=1)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = MaxPool2D(pool_size=2)(x)

    x = Conv2D(64, kernel_size=(3,3), strides=1)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    x = Flatten()(x)

    x = Dense(1024)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = Dropout(0.1)(x)

    x = Dense(256)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = Dropout(0.4)(x)

    x = Dense(10, activation='softmax')(x)

    sub_models.append(x)

x = keras.layers.average(sub_models)

main_output = keras.layers.average(sub_models)

model = Model(inputs=[main_input], outputs=[main_output])

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

print(model.summary())

plot_model(model, to_file='model.png')

filepath="weights.best.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
tensorboard = TensorBoard(log_dir='./Graph', histogram_freq=0, write_graph=True, write_images=True)
callbacks = [checkpoint, tensorboard]

model.fit_generator(datagen.flow(X_train, y_train, batch_size=128),
                    steps_per_epoch=len(X_train) / 128,
                    epochs=epochs,
                    callbacks=callbacks,
                    verbose=1,
                    validation_data=(X_test, y_test))

所以现在我只对最后一层进行平均，但我想在单独训练每一层后对所有层的权重进行平均。

谢谢！

Answer 1

因此，我们假设

models

是模型的集合。首先 - 收集所有权重：

weights = [model.get_weights() for model in models]

现在 - 创建新的平均权重：

new_weights = list()

for weights_list_tuple in zip(*weights):
    new_weights.append(
        [numpy.array(weights_).mean(axis=0)\
            for weights_ in zip(*weights_list_tuple)])

剩下的就是在新模型中设置这些权重：

new_model.set_weights(new_weights)

当然 - 平均权重可能是一个坏主意，但如果你尝试 - 你应该遵循这种方法。

Answer 2

我无法评论已接受的答案，但为了使其在

tensorflow 2.0

和

tf.keras

上工作，我必须将循环中的列表放入 numpy 数组：

new_weights = list()
for weights_list_tuple in zip(*weights): 
    new_weights.append(
        np.array([np.array(w).mean(axis=0) for w in zip(*weights_list_tuple)])
    )

如果不同的输入模型需要不同的权重，则需要将

np.array(w).mean(axis=0)

替换为

np.average(np.array(w),axis=0, weights=relative_weights)

，其中

relative_weights

是一个数组，其中包含每个模型的权重因子。