python - Keras 中的 GaussianDropout 与 Dropout 与 GaussianNoise

Question

谁能解释一下不同 dropout 样式之间的区别？来自documentation ，我假设 GaussianDropout 不是将一些单位降为零(dropout)，而是将这些单位乘以某个分布。但是在实际测试的时候，所有的单元都会被触动。结果看起来更像经典的 GaussianNoise。

tf.random.set_seed(0)
layer = tf.keras.layers.GaussianDropout(.05, input_shape=(2,))
data = np.arange(10).reshape(5, 2).astype(np.float32)
print(data)

outputs = layer(data, training=True)
print(outputs)

结果:

[[0. 1.]
 [2. 3.]
 [4. 5.]
 [6. 7.]
 [8. 9.]]
tf.Tensor(
[[0.    1.399]
 [1.771 2.533]
 [4.759 3.973]
 [5.562 5.94 ]
 [8.882 9.891]], shape=(5, 2), dtype=float32)

编辑:

显然，这就是我一直想要的:

def RealGaussianDropout(x, rate, stddev):

    keep_prob = 1 - rate
    random_tensor = tf.random.uniform(tf.shape(x))
    keep_mask = tf.cast(random_tensor >= rate, tf.float32)   
    noised = x + K.random_normal(tf.shape(x), mean=.0, stddev=stddev)   
    ret = tf.multiply(x, keep_mask) + tf.multiply(noised, (1-keep_mask))

    return ret


outputs = RealGaussianDropout(data,0.2,0.1)
print(outputs)

Answer 1

你是对的……GaussianDropout 和 GaussianNoise 非常相似。你可以自己复制它们来测试所有的相似性

def dropout(x, rate):

    keep_prob = 1 - rate
    scale = 1 / keep_prob
    ret = tf.multiply(x, scale)
    random_tensor = tf.random.uniform(tf.shape(x))
    keep_mask = random_tensor >= rate
    ret = tf.multiply(ret, tf.cast(keep_mask, tf.float32))
    
    return ret

def gaussian_dropout(x, rate):
    
    stddev = np.sqrt(rate / (1.0 - rate))
    ret = x * K.random_normal(tf.shape(x), mean=1.0, stddev=stddev)
    
    return ret

def gaussian_noise(x, stddev):
    
    ret = x + K.random_normal(tf.shape(x), mean=.0, stddev=stddev)
    
    return ret

高斯噪声只是将随机正态值与 0 均值相加，而高斯丢弃只是将随机正态值与 1 均值相乘。这些操作涉及输入的所有元素。经典的 dropout 将一些输入元素变为 0，对其他输入元素进行缩放

辍学

data = np.arange(10).reshape(5, 2).astype(np.float32)

set_seed(0)
layer = tf.keras.layers.Dropout(.4)
out1 = layer(data, training=True)
set_seed(0)
out2 = dropout(data, .4)
print(tf.reduce_all(out1 == out2).numpy()) # TRUE

高斯下降

data = np.arange(10).reshape(5, 2).astype(np.float32)

set_seed(0)
layer = tf.keras.layers.GaussianDropout(.05)
out1 = layer(data, training=True)
set_seed(0)
out2 = gaussian_dropout(data, .05)
print(tf.reduce_all(out1 == out2).numpy()) # TRUE

高斯噪声

data = np.arange(10).reshape(5, 2).astype(np.float32)

set_seed(0)
layer = tf.keras.layers.GaussianNoise(.3)
out1 = layer(data, training=True)
set_seed(0)
out2 = gaussian_noise(data, .3)
print(tf.reduce_all(out1 == out2).numpy()) # TRUE

为了保证可重复性，我们使用了 (TF2):

def set_seed(seed):
    
    tf.random.set_seed(seed)
    os.environ['PYTHONHASHSEED'] = str(seed)
    np.random.seed(seed)
    random.seed(seed)