我正在学习 RBM,并从 Hismael Costa 的 github 存储库中复制并分析了他的代码。我已经更改了代码,因此它仅适用于 tensorflow.v2。不知何故,当训练损失函数时,整个跳跃而不是下降。
数据集肯定是收敛的。
length = 64*100
col0 = np.random.randint(0,2,length)
col1 = np.random.randint(0,2,length)
col2 = np.bitwise_or(col0, col1)
train_X = np.array([col0, col1, col2], dtype=np.float32).T
最初我认为这是 GradientTape 的错误应用或错误的优化器语法,因为这是我主要自己编写的部分,但看起来还不错。隐藏节点的数量、learnig_rate 和步数都不会改变任何东西。我也尝试了 SGD 优化器,但无济于事。
有人可以看看我的代码吗:
import tensorflow as tf
import numpy as np
class RBM(tf.keras.Model):
def __init__(self, nv, nh, cd_steps=3):
super().__init__()
self.W = tf.Variable(tf.random.truncated_normal((nv, nh), dtype=tf.float64) * 0.01)
self.bv = tf.Variable(tf.zeros((nv, 1), dtype=tf.float64))
self.bh = tf.Variable(tf.zeros((nh, 1), dtype=tf.float64))
self.cd_steps = cd_steps
self.modelW = None
def bernoulli(self, p):
return tf.nn.relu(tf.sign(p- tf.random.uniform(p.shape, dtype=tf.float64)))
def sample_h(self, v):
ph_given_v = tf.sigmoid(tf.matmul(v, self.W) + tf.squeeze(self.bh))
return self.bernoulli(ph_given_v)
def sample_v(self, h):
pv_given_h = tf.sigmoid(tf.matmul(h, tf.transpose(self.W)) + tf.squeeze(self.bv))
return self.bernoulli(pv_given_h)
def gibbs_step(self, i, k, vk):
hk = self.sample_h(vk)
vk = self.sample_v(hk)
return i+1, k, vk
def energy(self, v):
b_term = tf.matmul(v, self.bv)
linear_tranform = tf.matmul(v, self.W) + tf.squeeze(self.bh)
h_term = tf.reduce_sum(tf.math.log(tf.exp(linear_tranform) + 1), axis=1)
return tf.reduce_mean(-h_term -b_term)
def loss(self, v, vk):
return self.energy(v) - self.energy(vk)
def call(self, X, lr=0.01, batch_size=64, epochs=5):
X = tf.data.Dataset.from_tensor_slices(X).batch(batch_size)
optimizer = tf.keras.optimizers.Adam(learning_rate=lr)
for epoch in range(epochs):
losses = []
for n_batch, batch in enumerate(X):
print('batch: ', n_batch, end='\r')
with tf.GradientTape() as tape:
v = batch
vk = tf.identity(v)
i = tf.constant(0)
_, _, vk = tf.nest.map_structure(tf.stop_gradient,
tf.while_loop(cond = lambda i,k, *args: i<=k,
body = self.gibbs_step,
loop_vars =[i, tf.constant(0), v])
)
l = self.loss(v, vk)
# grads = tape.gradient(l, [self.W, self.bv, self.bh])
# optimizer.apply_gradients(zip(grads, self.trainable_variables))
optimizer.minimize(l, var_list = [self.W, self.bv, self.bh], tape=tape) # this does the same job as the 2 lines abow (doesn't it?)
losses.append(l)
print('Epoch: {} Cost: {}'.format(epoch, np.mean(losses)))
self.modelW = self.W
def predict(self, Q, batch_size=64):
Q = tf.data.Dataset.from_tensor_slices(Q).batch(batch_size)
answers = []
for n_batch, batch in enumerate(Q):
print('batch: ', n_batch, end='\r')
v = batch
i = tf.constant(0)
_, _, vk = tf.nest.map_structure(tf.stop_gradient,
tf.while_loop(cond = lambda i,k, *args: i<=k,
body = self.gibbs_step,
loop_vars =[i, tf.constant(0), v])
)
answers.append(vk.numpy())
return np.concatenate(answers)
只需执行以下代码即可使用数据集运行类。
rbm = RBM(nv=train_X.shape[1], nh=5, cd_steps=3)
rbm(X=train_X, lr=0.001, epochs=10)