Comments (7)
boost的引用也报错,我include的路径没有改呀
D:\deepid\3rdparty\include\boost/mpl/assert.hpp(152): error C2653: “type”: 不是类或命名空间名称
D:\deepid\3rdparty\include\boost/mpl/assert.hpp(153): 参见对正在编译的类 模板 实例化“boost::mpl::eval_assert”的引用
from caffe-windows.
第一个错误是我在修复一个bug的时候把中途的一个版本上传了。
你把alpha改成alpha()就行了。
第二个你把错误贴全,贴出哪一句话引发的错误。
from caffe-windows.
感谢你耐心的回答,第一个错误已经改掉了,第二个是我的boost版本的问题,换上你的就可以了。
还向你请教一下,我mnist数据训练完成了,怎么测试一下。有没有test的脚本给我分享一下,谢谢。
from caffe-windows.
在训练的过程中已经做过测试了,里面的Test net output #0: accuracy = XXX就是测试结果了。
from caffe-windows.
我运行了一次你看看这个结果对不
I0611 19:27:03.528997 9044 solver.cpp:276] Iteration 10000, loss = 0.00183815
I0611 19:27:03.528997 9044 solver.cpp:294] Iteration 10000, Testing net (#0)
I0611 19:27:03.946022 9044 solver.cpp:343] Test net output #0: accuracy = 0.9914
I0611 19:27:03.947021 9044 solver.cpp:343] Test net output #1: loss = 0.0265216 (* 1 = 0.0265216 loss)
I0611 19:27:03.947021 9044 solver.cpp:281] Optimization Done.
I0611 19:27:03.948021 9044 caffe.cpp:134] Optimization Done.
这个结果对不
from caffe-windows.
嗯,就是这个结果。
from caffe-windows.
ok,谢谢。
from caffe-windows.
Related Issues (20)
- how to use Contrastive/Triplet loss layer? Is there any train_val.ptototxt example?
- Accessing .\windows
- building caffe issue fatal error LNK1104 cannot open file python36.lib HOT 6
- can not compile in the windows
- python3.5报错LINK : fatal error LNK1104: 无法打开文件“python36.lib” HOT 2
- Can not find the prototxt including the LabelSpecificAdd
- fatal error: caffe/proto/caffe.pb.h: No such file or directory HOT 1
- softmax_loss = 0 ,under ubuntu16.04,cuda10,opencv 3.4.5
- caffe_pb2.py has no LabelMap() HOT 1
- win10+cuda10+cudnn7.3编译出现MSB271错误? HOT 3
- 编译出现:InitLogLevelPipe错误
- python3.5
- Compile on ubuntu
- mnist demo failed
- compile error on win10 + VS2017 + cuda9
- after deleting a Net instance, the GPU memory is not released
- 求助大佬,win7 64位,vs2015+cuda10.2 环境下编译需要如何修改啊?
- 0 projects, projects or modules unavailable
- cuda11.1+win10+vs2015+rtx3090 NetParameter problem
- libcaffe编译成功,pycaffe 编译失败
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from caffe-windows.