Keras 自定義層

 １．對於簡單的定制操作，可以通過使用layers.core.Lambda層來完成。該方法的適用情況：僅對流經該層的數據做個變換，而這個變換本身沒有需要學習的參數．

# 切片后再分別進行embedding和average pooling
import numpy as np  
from keras.models import Sequential  
from keras.layers import Dense, Activation,Reshape  
from keras.layers import merge  
from keras.utils import plot_model
from keras.layers import *
from keras.models import Model  

def get_slice(x, index):
    return x[:, index]

keep_num = 3 
field_lens = 90
input_field = Input(shape=(keep_num, field_lens))
avg_pools = []
for n in range(keep_num):
    block = Lambda(get_slice,output_shape=(1,field_lens),arguments={'index':n})(input_field)
    x_emb = Embedding(input_dim=100, output_dim=200, input_length=field_lens)(block)
    x_avg = GlobalAveragePooling1D()(x_emb)
    avg_pools.append(x_avg)  
output = concatenate([p for p in avg_pools])
model = Model(input_field, output) 
plot_model(model, to_file='model/lambda.png',show_shapes=True)  

plt.figure(figsize=(21, 12))
im = plt.imread('model/lambda.png')
plt.imshow(im)

 這里用Lambda定義了一個對張量進行切片操作的層

 

 

２．對於具有可訓練權重的定制層，需要自己來實現。 

from keras import backend as K
from keras.engine.topology import Layer
import numpy as np

class MyLayer(Layer):

    def __init__(self, output_dim, **kwargs):
        self.output_dim = output_dim
        super(MyLayer, self).__init__(**kwargs)

    def build(self, input_shape):
        # Create a trainable weight variable for this layer.
        self.kernel = self.add_weight(name='kernel', 
                                      shape=(input_shape[1], self.output_dim),
                                      initializer='uniform',
                                      trainable=True)
        super(MyLayer, self).build(input_shape)  # Be sure to call this somewhere!

    def call(self, x):
        return K.dot(x, self.kernel)

    def compute_output_shape(self, input_shape):
        return (input_shape[0], self.output_dim)

 

參考：

Writing your own Keras layers Keras官方文檔，中文文檔

keras Lambda自定義層實現數據的切片,Lambda傳參數

keras中自定義Layer

如何利用Keras的擴展性