實現乙個簡單層需要首先繼承 layers.layer 類即可,如下是官方**上的例子:
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)
正常dl都是乙個forward, backword, update 三個流程,而在 keras 中對於單層 layer 來說,通過將可訓練的權應該在這裡被加入列表`self.trainable_weights中。其他的屬性還包括self.non_trainabe_weights（列表）和self.updates（需要更新的形如（tensor, new_tensor）的tuple的列表）。你可以參考batchnormalization層的實現來學習如何使用上面兩個屬性。這個方法必須設定self.built = true，可通過呼叫super([layer],self).build()實現
詳細檢視了下 add_weight 函式實現如下（keras/engine/topology.py）：
def add_weight(self,
name,
shape,
dtype=none,
initializer=none,
regularizer=none,
trainable=true,
constraint=none):
"""adds a weight variable to the layer.
# arguments
name: string, the name for the weight variable.
shape: the shape tuple of the weight.
dtype: the dtype of the weight.
initializer: an initializer instance (callable).
regularizer: an optional regularizer instance.
trainable: a boolean, whether the weight should
be trained via backprop or not (assuming
that the layer itself is also trainable).
constraint: an optional constraint instance.
# returns
the created weight variable.
"""initializer = initializers.get(initializer)
if dtype is none:
dtype = k.floatx()
weight = k.variable(initializer(shape),
dtype=dtype,
name=name,
constraint=constraint)
if regularizer is not none:
self.add_loss(regularizer(weight))
if trainable:
else:
return weight
具體訓練過程參見: keras/engine/training.py
Keras學習筆記
手冊 keras中文文件 1.張量 一階張量是向量，二階張量是矩陣。2.batch batch gradient descent,遍歷全部資料集算一次損失函式，然後算函式對各個引數的梯度，更新梯度。太慢。stochastic gradient descent，每看乙個資料就算一下損失函式，然後求梯度...
Keras筆記 3 關於Keras的模型型別
keras有兩種型別的模型，序貫模型 sequential 和函式式模型 model 函式式模型應用更為廣泛，序貫模型是函式式模型的一種特殊情況。兩類模型有一些方法是相同的 config model.get config model model.from config config or,for s...
keras學習筆記1 Keras模組概述
keras主要包括14個模組，本文主要對models layers initializations activations objectives optimizers preprocessing metrics共計8個模組分別展開介紹，並通過乙個簡單的bp神經網路說明各個模組的作用。1.model ...