jeremyong / cpp_nn_in_a_weekend Goto Github PK
View Code? Open in Web Editor NEWArticle and source code reference to construct a C++ neural network in a weekend without any dependencies
Article and source code reference to construct a C++ neural network in a weekend without any dependencies
Hi Jeremy,
first of all thanks for that very helpfull tutorial, I guess that you shall solve my problem immediately.
1. If I run the start command from my console like that:
cd C:\Users\Sabi\Documents\Visual Studio 2019\NeuralNetwork-Cpp-02\out\build\x64-Debug (Standard)\src
nn.exe train ../../../../data/train
nn.exe evaluate ../../../../data/test ./ff.params
All is working fine without any error
OK
2. But if I try to run it from the VS Run button with this code in main.cpp:
// Bangert eingefügt
// char* dummy_args[] = {"../../../../data/test", "evaluate", "./ff.params"};
char* dummy_args[] = {"../../../../data/test", "train", "./ff.params"};
int argc_dummy = 3;
// Bangert Ende
int main(int argc, char* argv[])
{
// Bangert eingefügt
argv = dummy_args;
argc = argc_dummy;
// Bangert Ende
.
.
.
NOT OK
Error in line 29 of MNIST.cpp - read_be(images, &image_count_) :
Unbehandelte Ausnahme bei 0x00007FFC3423D759 in nn.exe: Microsoft C++-Ausnahme: std::runtime_error bei Speicherort 0x00000032C56FF018
What might be the cause? I can't solve it. I guess it depends on the right expression for teh model ff params std::ios::binary
Best thanks and regards
Axel
Would be great if you could also export the doc to epub so I can throw it on my e-reader.
I would do it myself, but pandoc gives me trouble.
To generate your blog, it looks simply gorgeous, your primary writing/formatting tool is LaTeX or something else? I would like to use the same toolchain for my blog. Thanks in advance for your answer.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.