TensorFlow：爲預先訓練好的權重添加一個小噪聲

Question

我已經完成了3個LSTM的堆棧訓練，現在我想調查每個LSTM層對它的權重的小擾動有多敏感。我想從檢查點加載模型，爲某個圖層的權重添加一個小值並記錄性能損失/收益。我不知道最簡單的方法是什麼？

Answer 1

import tensorflow as tf 

# define model 
... 

# load checkpoint 
... 

# assemble the list of weights to add noise 
list_of_weights = [ ... ] 


def add_random_noise(w, mean=0.0, stddev=1.0): 
    variables_shape = tf.shape(w) 
    noise = tf.random_normal(
     variables_shape, 
     mean=mean, 
     stddev=stddev, 
     dtype=tf.float32, 
    ) 
    return tf.assign_add(w, noise) 


sess = tf.Session() 
for w in list_of_weights: 
    sess.run(add_random_noise(w)) 

# continue experiments 
...