随笔分类 -  tensorflow

TensorFlow 报错 ValueError: Can't load save_path when it is None.
摘要：原因 : 模型还未生成出来 , 此时你去检测的生成完毕的模型 , 模型呢 ? 还没生成 . 模型还没生成就引用了为什么不报错 ? 解决办法 : 当前情况不要以为是你的程序有 bug , 而是你的模型还没生成完毕 , OVER ! 阅读全文
posted @ 2019-09-16 22:05 anobscureretreat 阅读(3535) 评论(0) 推荐(0) 编辑
2019-09-16 16:42:03.621946: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA Traceback (most recent cal
摘要：在文件开始加入 阅读全文
posted @ 2019-09-16 22:04 anobscureretreat 阅读(556) 评论(0) 推荐(0) 编辑
utility.py:61: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array in
摘要：解决：使用tuple转换一次 one_hot_label[tuple(one_hot_index)] = 1.0 阅读全文
posted @ 2019-09-16 22:03 anobscureretreat 阅读(1198) 评论(0) 推荐(0) 编辑
W tensorflow/core/platform/cpu_feature_guard.cc:45]
摘要：W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations. W t... 阅读全文
posted @ 2019-06-15 22:02 anobscureretreat 阅读(1046) 评论(0) 推荐(0) 编辑

点击右上角即可分享
微信分享提示