- 博客(10)
- 收藏
- 关注
原创 Session was not created with a graph before Run()!
Session was not created with a graph before Run()!1.问题怎么出现的:Ubuntu下python训练的TensorFlow模型封装成pb文件之后,在win10下安装C++版TensorFlow,调用pb文件,重写预处理和后处理部分,封装成dll之后,用c#调用的时候出现这个问题。2.问题分析:C#程序未能成功找到pb文件的位置3.问题解决:首先用下面代码在C#中找到当前工作目录 Console.WriteLine(System.IO.D
2021-05-11 17:04:23
416
原创 tensorflow保存的ckpt,meta模型freeze成pb
参考:https://blog.youkuaiyun.com/yjl9122/article/details/78341689使用博主方法时遇到两个问题:1.freeze的时候参数没写全会报错。(解决办法:参数最好写全,无论必选还是可选项)2.加载.meta文件的时候,设置input_binary为False会报错。修改free_graph_meta.py文件时,修改位置跟博主的位置行号对应不上。(解决方法:Ctrl+F 检索所有input_graph_def =的行,把所有行都修改了)博主代码如下:impo
2021-04-14 16:16:25
710
原创 win10 c++编译TensorFlow1.13.1 GPU版
Ubuntu16.04 CUDA10.2 CUDNN7.6.5 tensorflow1.13.1下训练的网络,封装成pb模型,在win10下调用,需要先编译TensorFlow。一开始尝试编译GPU的版本,踩坑没爬上来。先编译一个CPU版本的试试,回头有机会再搞GPU的。参考:https://blog.youkuaiyun.com/atpalain_csdn/article/details/97945536,https://blog.youkuaiyun.com/weixin_43868576/article/details/1
2021-03-23 10:13:34
1011
原创 ValueError: You are trying to load a weight file containing 4 layers into a model with 0 layers.
ValueError: You are trying to load a weight file containing 4 layers into a model with 0 layers.已经训练好模型,并保存为Simcnn.h5文件,模型重新编译并调用的时候报错。出错代码: def model_pre(self): if os.path.exists("ckpt/Simcnn/checkpoint/Simcnn.h5"): Simcnn.model.loa
2020-09-29 15:39:27
772
原创 TypeError: ‘numpy.float64‘ object cannot be interpreted as an integer类型出错
TypeError: ‘numpy.float64’ object cannot be interpreted as an integer出错代码: for i in range(overlap_ranges.shape[1]): for j in range(overlap_ranges.shape[2]): min_overlaps[:, i, j] = np.linspace(*overlap_ranges[:, i, j])输入:overlap_
2020-09-05 12:00:11
1263
原创 VS2019+PCL1.9.1配置
VS2017下载与安装可以参考:https://blog.youkuaiyun.com/weixin_41991128/article/details/83656543https://blog.youkuaiyun.com/qq_33528803/article/details/97399915本文在第二篇博客基础上,增加了报错修改,并对原文中最后一步版...
2020-07-07 14:28:00
1780
2
转载 NVIDIA-SMI has failed because it couldn't communicate with the NVIDIA driver. Make sure that the lat
2019年06月22日 出现这个问题之后参考了一篇博客https://blog.youkuaiyun.com/sinat_23619409/article/detail...
2019-06-22 15:24:27
15838
5
原创 从零开始安装双系统Ubuntu18.04、CUDA、cuDNN、TensorFlow-GPU
转载:https://blog.youkuaiyun.com/blgpb/article/details/82048478 从零开始安装双系统Ubuntu18.04、CUDA、cuDNN、TensorFlow-GPU ...
2019-06-20 09:55:16
549
转载 ubuntu18.04安装tensorflow-gpu
转载:https://blog.youkuaiyun.com/u014670893/article/details/82467384 ubuntu18.04 安装tensorflow-gpu 2018年0...
2019-06-20 09:49:44
487
转载 tensorflow-gpu,CUDA与CUDNN版本对应关系
转载自:https://blog.youkuaiyun.com/Young__Fan/article/details/88130385当在安装Tensorflow的时候,若我们直接使用以下指令:pip install tensorflow-gpu或:pip install --ignore-installed --upgrade tensorflow-gpu这样的话,安装的会是最新版的ten...
2019-06-18 20:30:04
688
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人