我的环境是WIN7+Pycharm+Python3.6运行的。 第三章中训练自己的模型,运行train_image_classifier.py会出现错误如下: No node-device colocations were active during op ‘InceptionV3/Conv2d_1a_3x3/weights/Initializer/truncated_normal/TruncatedNormal’ creation. Device assignments active during op ‘InceptionV3/Conv2d_1a_3x3/weights/Initializer/truncated_normal/TruncatedNormal’ creation: with tf.device(None): <C:\Program Files (x86)\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\variables.py:1435> with tf.device(): <C:\Program Files (x86)\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\contrib\framework\python\ops\variables.py:264> with tf.device(/device0): <C:\Users\Administrator\Desktop\New\DL\3myset\slim\deployment\model_deploy.py:190>
ERROR================================== Object was never used (type <class 'tensorflow.python.framework.ops.Tensor'>):
<tf.Tensor 'init_ops/report_uninitialized_variables/boolean_mask/GatherV2:0' shape=(?,) dtype=string> If you want to mark it as used call its “mark_used()” method.
请问何老师还在不?
第六章6.4.3 LFW数据库上人脸检测和对齐 出现的问题 我的是windows下CPU版本的
附上书上的原图,如果是系统的问题那就~
我的环境是WIN7+Pycharm+Python3.6运行的。
第三章中训练自己的模型,运行train_image_classifier.py会出现错误如下:
No node-device colocations were active during op ‘InceptionV3/Conv2d_1a_3x3/weights/Initializer/truncated_normal/TruncatedNormal’ creation.
Device assignments active during op ‘InceptionV3/Conv2d_1a_3x3/weights/Initializer/truncated_normal/TruncatedNormal’ creation:
with tf.device(None): <C:\Program Files (x86)\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\variables.py:1435>
with tf.device(): <C:\Program Files (x86)\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\contrib\framework\python\ops\variables.py:264>
with tf.device(/device0): <C:\Users\Administrator\Desktop\New\DL\3myset\slim\deployment\model_deploy.py:190>
ERROR==================================
Object was never used (type <class 'tensorflow.python.framework.ops.Tensor'>):
<tf.Tensor 'init_ops/report_uninitialized_variables/boolean_mask/GatherV2:0' shape=(?,) dtype=string>
If you want to mark it as used call its “mark_used()” method.
想用Pycharm直接运行这个程序,需要改哪些参数设置呢?还有,这个报错的问题出在哪里?看了两天了,没有头绪。
那个里面?
老师你好,请问为什么第二章2.2.3训练模型我的训练速度非常非常慢呢,我安装了tensoflow-gpu==1.10.0,并且测试能正常运行,但是运行2.2.3的代码的时候训练速度非常非常慢,求老师解答