tensorflow
aliceDingYM
这个作者很懒,什么都没留下…
展开
-
cnn实现 saver()
from __future__ import print_functionimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets('MNIST_data',one_hot=True)def comput原创 2017-09-27 16:31:29 · 290 阅读 · 0 评论 -
could not destroy cudnn handle: CUDNN_STATUS_BAD_PARAM
without close of session,you can use method 1, with tf.session or sess.close()1.config = tf.ConfigProto(device_count = {'GPU': 0})config.gpu_options.allow_growth = Truewith tf.Session(config=c原创 2017-09-27 16:17:08 · 741 阅读 · 0 评论 -
droputout使用
from __future__ import print_functionimport tensorflow as tf from sklearn.datasets import load_digitsfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import Label转载 2017-09-26 11:42:08 · 1012 阅读 · 0 评论 -
tf.cast
cast(x, dtype, name=None) 将x的数据格式转化成dtype.例如,原来x的数据格式是bool, 那么将其转化成float以后,就能够将其转化成0和1的序列。反之也可以a = tf.Variable([1,0,0,1,1])b = tf.cast(a,dtype=tf.bool)sess = tf.Session()sess.run(tf.initializ转载 2017-09-25 17:36:16 · 207 阅读 · 0 评论 -
The TensorFlow library wasn't compiled to use SSE4.1 instructions
原文转自2017-05-06 08:09:33.780033: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine a转载 2017-09-25 15:48:55 · 485 阅读 · 0 评论 -
GPU 版 TensorFlow failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
如果你是使用 GPU 版 TensorFlow 的话,并且你想在显卡高占用率的情况下(比如玩游戏)训练模型,那你要注意在初始化 Session 的时候为其分配固定数量的显存,否则可能会在开始训练的时候直接报错退出:2017-06-27 20:39:21.955486: E c:\tf_jenkins\home\workspace\release-win\m\windows-gpu\py\35\转载 2017-09-22 18:01:32 · 13585 阅读 · 0 评论 -
tensorflow导入报错ModuleNotFoundError: No module named '_pywrap_tensorflow_internal'
全部报错Traceback (most recent call last): File "C:\。。。。\Python\Python36\lib\site-packages\tensorflow\python\pywrap_tensorflow.py", line 41, in from tensorflow.python.pywrap_tensorflow_internal原创 2017-07-19 11:29:29 · 24267 阅读 · 1 评论 -
tensorflow session两种运行
对于tensorflow ,只有运行到session.run(xxx),才会调用起计算图里的该计算xxx因此大概有两种方式运行1,sess = tf.Session()for i in range(20000):result=sess.run(xxx)sess.close()2,用with的方法with tf.Session()as sess:原创 2017-09-22 15:45:36 · 1255 阅读 · 0 评论