[英]How do I get the weights of a layer in Keras?
我使用的是 Windows 10、Python 3.5 和 tensorflow 1.1.0。 我有以下腳本:
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()
我收到錯誤: AttributeError: 'Tensor' object has no attribute 'weights'
如果你想獲得所有層的權重和偏差,你可以簡單地使用:
for layer in model.layers: print(layer.get_config(), layer.get_weights())
這將打印所有相關信息。
如果您希望權重直接作為 numpy 數組返回,您可以使用:
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。
如果你寫:
dense1 = Dense(10, activation='relu')(input_x)
那么dense1
不是一層,而是一層的輸出。 該層為Dense(10, activation='relu')
所以看來你的意思是:
dense1 = Dense(10, activation='relu')
y = dense1(input_x)
這是一個完整的片段:
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()
如果您想查看層的權重和偏差如何隨時間變化,您可以添加一個回調來記錄每個訓練時期的值。
例如,使用這樣的模型,
import numpy as np
model = Sequential([Dense(16, input_shape=(train_inp_s.shape[1:])), Dense(12), Dense(6), Dense(1)])
在擬合期間添加回調 **kwarg:
gw = GetWeights()
model.fit(X, y, validation_split=0.15, epochs=10, batch_size=100, callbacks=[gw])
其中回調定義為
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))
此回調將構建一個包含所有層權重和偏差的字典,並以層數標記,因此您可以看到它們在模型訓練時隨時間的變化。 您會注意到每個權重和偏置數組的形狀取決於模型層的形狀。 為模型中的每一層保存一個權重數組和一個偏置數組。 第三個軸(深度)顯示了它們隨時間的演變。
在這里,我們使用了 10 個 epoch 和一個具有 16、12、6 和 1 個神經元層的模型:
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)
如果圖層索引號令人困惑,您也可以使用圖層名稱
重量:
model.get_layer(<<layer_name>>).get_weights()[0]
偏見:
model.get_layer(<<layer_name>>).get_weights()[1]
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.