AttributeError: module 'tensorflow' has no attribute 'select'

最新推荐文章于 2024-06-15 06:46:14 发布

原创最新推荐文章于 2024-06-15 06:46:14 发布 · 2.2k 阅读

1 ·

CC 4.0 BY-SA版权

机器学习专栏收录该内容

2 篇文章

订阅专栏

本文通过TensorFlow实现了一个自定义损失函数的例子，并采用Adam优化器进行参数调整。使用随机生成的数据集训练了一个简单的线性模型，展示了如何定义不均衡损失并应用于训练过程中。

部署运行你感兴趣的模型镜像

# p79自定义损失函数
import tensorflow as tf
from numpy.random import RandomState
batch_size = 8

x = tf.placeholder(tf.float32, shape = (None,2),name = 'x-input')
y_ = tf.placeholder(tf.float32, shape = (None,1),name = 'y-input')
w1 = tf.Variable(tf.random_normal([2,1],stddev = 1,seed = 1))
y = tf.matmul(x,w1)
loss_less = 10
loss_more = 1
loss = tf.reduce_sum(tf.select(tf.greater(y_,y), (y-y_) * loss_more, (y_-y) * loss_less))
train_step = tf.train_AdamOptimizer(0.001).minimize(loss)
rdm = RandomState(1)
dataset_size = 128
X = rdm.rand(dataset_size,2)
Y = [[x1+x2+rdm.rand()/10.0-0.05] for (x1,x2) in X]
with tf.Session() as sess:
    init_op = tf.initialize_all_variables()
    sess.run(init_op)
    STEP = 5000
    for i in range(STEP):
        start = (i * batch_size) % dataset_size
        end = min(start+batch_size, dataset_size)
        sess.run(train_step, feed_dict = {x:X[start:end], y:Y[start:end]})
        print(sess.run(w1))