tensorflow 2.0 随机梯度下降 之 单输出感知机梯度

版权声明：本文为博主（[email protected]）原创文章，未经博主允许不得转载。 https://blog.csdn.net/z_feng12489/article/details/90033434

单一输出感知机

x=tf.random.normal([1,3])

w=tf.ones([3,1])

b=tf.ones([1])

y = tf.constant([1])


with tf.GradientTape() as tape:

	tape.watch([w, b])
	logits = tf.sigmoid(x@w+b) 
	loss = tf.reduce_mean(tf.losses.MSE(y, logits))

grads = tape.gradient(loss, [w, b])
print('w grad:', grads[0])

print('b grad:', grads[1])

w grad: tf.Tensor(
[[-0.10537013]
 [ 0.11153423]
 [ 0.32909304]], shape=(3, 1), dtype=float32)
b grad: tf.Tensor([-0.27427486], shape=(1,), dtype=float32)