Keras遮罩输出层

时间:2019-04-13 20:43:27

标签: python keras conv-neural-network

我在Keras中具有以下模型:

main_input = Input(shape=(None, 2, 100, 100), dtype='float32', name='input')

hidden = ConvLSTM2D(filters=16, 
                    kernel_size=(5, 5),  
                    padding='same', 
                    return_sequences=False, 
                    data_format='channels_first')(main_input)

output = Conv2D(filters=1, 
                kernel_size=(1, 1), 
                padding='same',
                activation='sigmoid',
                kernel_initializer='glorot_uniform',
                data_format='channels_first',
                name='output')(hidden)

sgd = SGD(lr=0.002, momentum=0.0, decay=0.0, nesterov=False)

我想将2d数组的输出乘以一个掩码(每个示例都有一个单独的掩码)。我如何在Keras中做到这一点?

3 个答案:

答案 0 :(得分:2)

使用tensorflow 2.0和tf.keras进行这项工作。

import tensorflow as tf
from tensorflow.keras.layers import Multiply, Conv2D, ConvLSTM2D, Input

main_input = Input(shape=(None, 2, 100, 100), dtype='float32', name='input')

mask=Input(shape=(1, 100, 100), dtype='float32', name='mask')

hidden = ConvLSTM2D(filters=16, 
                    kernel_size=(5, 5),  
                    padding='same', 
                    return_sequences=False, 
                    data_format='channels_first')(main_input)

output = Conv2D(filters=1, 
                kernel_size=(1, 1), 
                padding='same',
                activation='sigmoid',
                kernel_initializer='glorot_uniform',
                data_format='channels_first',
                name='output')(hidden)
output_with_mask=Multiply()([output, mask])

答案 1 :(得分:1)

我认为您应该同时将每个样本的蒙版输入模型。

这是建议的代码:

from keras.layers import Multiply

main_input = Input(shape=(None, 2, 100, 100), dtype='float32', name='input')

mask=Input(shape=(1, 100, 100), dtype='float32', name='mask')

hidden = ConvLSTM2D(filters=16, 
                    kernel_size=(5, 5),  
                    padding='same', 
                    return_sequences=False, 
                    data_format='channels_first')(main_input)

output = Conv2D(filters=1, 
                kernel_size=(1, 1), 
                padding='same',
                activation='sigmoid',
                kernel_initializer='glorot_uniform',
                data_format='channels_first',
                name='output')(hidden)
output_with_mask=Multiply()([output, mask])

model=Model([main_input, mask], output_with_mask)

摘要如下:

    __________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input (InputLayer)              (None, None, 2, 100, 0                                            
__________________________________________________________________________________________________
conv_lst_m2d_7 (ConvLSTM2D)     (None, 16, 100, 100) 28864       input[0][0]                      
__________________________________________________________________________________________________
output (Conv2D)                 (None, 1, 100, 100)  17          conv_lst_m2d_7[0][0]             
__________________________________________________________________________________________________
mask (InputLayer)               (None, 1, 100, 100)  0                                            
__________________________________________________________________________________________________
multiply_7 (Multiply)           (None, 1, 100, 100)  0           output[0][0]                     
                                                                 mask[0][0]                       
==================================================================================================
Total params: 28,881
Trainable params: 28,881
Non-trainable params: 0
__________________________________________________________________________________________________

答案 2 :(得分:0)

创建一个新输出,并将您的旧输出用作第二个隐藏层。

您想在“旧输出”上进行第二次卷积(带有特殊掩码)以获取新输出

希望对您有帮助