报错描述:
在训练facenet时遇到如下报错 Expected int32, got list containing Tensors of type '_Message' instead.
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-3-695ac180e28b> in <module>()
11 phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
12
---> 13 embeddings = network.inference(images_placeholder, FLAGS.pool_type, FLAGS.use_lrn, 1.0, phase_train=phase_train_placeholder)
14
15 # embeddings = network.inference(images_placeholder, 'MAX', False, 1.0, phase_train=phase_train_placeholder)
/home/cqh2/Desktop/yobiface-master/src/models/nn4.pyc in inference(images, pool_type, use_lrn, keep_probability, phase_train)
24 pool3 = facenet.mpool(lrn2,

在使用facenet训练时遇到了一个错误:Expected int32, got list containing Tensors of type '_Message'。错误的根本原因是TensorFlow版本不兼容。解决方案在于检查并更新facenet.py中的inception方法,可能需要适应当前TensorFlow库的版本需求进行代码调整。"
115767289,8740270,机器学习中的熵(Entropy)概念详解,"['机器学习', '信息熵', '统计学习', '数据挖掘']
最低0.47元/天 解锁文章
2000

被折叠的 条评论
为什么被折叠?



