Keras 2.x - 获取图层权重

Question

我使用的是Windows 10,Python 3.5和tensorflow 1.1.0.我有以下脚本:

import tensorflow as tf
import tensorflow.contrib.keras.api.keras.backend as K
from tensorflow.contrib.keras.api.keras.layers import Dense

tf.reset_default_graph()
init = tf.global_variables_initializer()
sess =  tf.Session()
K.set_session(sess) # Keras will use this sesssion to initialize all variables

input_x = tf.placeholder(tf.float32, [None, 10], name='input_x')    
dense1 = Dense(10, activation='relu')(input_x)

sess.run(init)

dense1.get_weights()

我收到错误: AttributeError: 'Tensor' object has no attribute 'weights'

我做错了什么,我怎么得到权重dense1？我看过这个和这个 SO帖子,但我仍然无法使它工作.

Answer 1

如果您想获得所有图层的权重和偏差,您可以简单地使用:

for layer in model.layers: print(layer.get_config(), layer.get_weights())

这将打印所有相关信息.

如果要将权重直接返回为numpy数组,可以使用:

first_layer_weights = model.layers[0].get_weights()[0]
first_layer_biases  = model.layers[0].get_weights()[1]
second_layer_weights = model.layers[1].get_weights()[0]
second_layer_biases  = model.layers[1].get_weights()[1]

等等

Answer 2

如果你写:

dense1 = Dense(10, activation='relu')(input_x)

然后dense1不是图层,它是图层的输出.这层是Dense(10, activation='relu')

所以看来你的意思是:

dense1 = Dense(10, activation='relu')
y = dense1(input_x)

这是一个完整的片段:

import tensorflow as tf
from tensorflow.contrib.keras import layers

input_x = tf.placeholder(tf.float32, [None, 10], name='input_x')    
dense1 = layers.Dense(10, activation='relu')
y = dense1(input_x)

weights = dense1.get_weights()

Answer 3

如果您想查看层的权重和偏差如何随时间变化，您可以添加一个回调来记录每个训练时期的值。

例如，使用这样的模型，

import numpy as np
model = Sequential([Dense(16, input_shape=(train_inp_s.shape[1:])), Dense(12), Dense(6), Dense(1)])

在拟合期间添加回调 **kwarg：

gw = GetWeights()
model.fit(X, y, validation_split=0.15, epochs=10, batch_size=100, callbacks=[gw])

其中回调定义为

class GetWeights(Callback):
    # Keras callback which collects values of weights and biases at each epoch
    def __init__(self):
        super(GetWeights, self).__init__()
        self.weight_dict = {}

    def on_epoch_end(self, epoch, logs=None):
        # this function runs at the end of each epoch

        # loop over each layer and get weights and biases
        for layer_i in range(len(self.model.layers)):
            w = self.model.layers[layer_i].get_weights()[0]
            b = self.model.layers[layer_i].get_weights()[1]
            print('Layer %s has weights of shape %s and biases of shape %s' %(
                layer_i, np.shape(w), np.shape(b)))

            # save all weights and biases inside a dictionary
            if epoch == 0:
                # create array to hold weights and biases
                self.weight_dict['w_'+str(layer_i+1)] = w
                self.weight_dict['b_'+str(layer_i+1)] = b
            else:
                # append new weights to previously-created weights array
                self.weight_dict['w_'+str(layer_i+1)] = np.dstack(
                    (self.weight_dict['w_'+str(layer_i+1)], w))
                # append new weights to previously-created weights array
                self.weight_dict['b_'+str(layer_i+1)] = np.dstack(
                    (self.weight_dict['b_'+str(layer_i+1)], b))

此回调将构建一个包含所有层权重和偏差的字典，并以层数标记，因此您可以看到它们在模型训练时随时间的变化。您会注意到每个权重和偏置数组的形状取决于模型层的形状。为模型中的每一层保存一个权重数组和一个偏置数组。第三个轴（深度）显示了它们随时间的演变。

在这里，我们使用了 10 个时期和一个具有 16、12、6 和 1 个神经元层的模型：

for key in gw.weight_dict:
    print(str(key) + ' shape: %s' %str(np.shape(gw.weight_dict[key])))

w_1 shape: (5, 16, 10)
b_1 shape: (1, 16, 10)
w_2 shape: (16, 12, 10)
b_2 shape: (1, 12, 10)
w_3 shape: (12, 6, 10)
b_3 shape: (1, 6, 10)
w_4 shape: (6, 1, 10)
b_4 shape: (1, 1, 10)

Answer 4

如果图层索引号令人困惑，您也可以使用图层名称

重量：

model.get_layer(<<layer_name>>).get_weights()[0]

偏见：

model.get_layer(<<layer_name>>).get_weights()[1]