问题标签 [fann]

My neural network has 22 inputs of 5184 values (two digit values, images converted to bytes), and I tried to set 2 output neurons with value 0 or 1, like:

From training results :

What is this bit fail? The documentation says:

The number of fail bits; means the number of output neurons which differ more than the bit fail limit.

How can I have 33 output neurons fail for only 2 output neurons? I imagine this 33 could be from a total of 44 outputs (2 from each of the 22 inputs). But documentation does not confirm this.

fann2我今天的问题是关于Python 2 包的奇怪行为，同时使用matplotlib或pyqtgraph同时使用。

假设我需要实时绘制我的 FANN 网络 MSE。然后我将使用matplotlib交互性和一些while True循环或Thread更新我的情节。但为简单起见，让我们举一个下面的例子。

以下脚本将创建一个新的神经网络并将其存储到一个文件中：

请注意PLOT当前禁用绘图的标志。

现在让我们看一下输出文件。让我们看看最后一行：

（...表示更多省略的字符）

一切都很好，直到我们将PLOTvalue 更改为True... 之后，相应的行将如下所示：

这会导致加载保存的网络时出错。例子：

给出以下错误：FANN Error 4: Error reading "connection_rate" from configuration file "my_network.ann".

有人知道如何解决这个奇怪的问题吗？也许我应该简单地在 matplotlib 的某个地方更改浮点数格式？我已经搜索了他们的文档，但还没有找到如何做到这一点。

我想这个原因在别的地方。这很有趣，但 PyQtGraph 给出了相同的结果。这是一个奖励脚本：

我需要安装 fann2 的帮助——FANN Python 绑定我有一台 Windows 7 机器。安装了 Anaconda 64bit 和 FANN 我正在尝试使用 pip install fann2 安装 Python 绑定。找不到库 doublefann ld.exe：找不到 -ldoublefann 我使用 easy_install 收到类似的消息

C_INCLUDE_PATH

这是 pip.log

Source in c:\users\myid~1\appdata\local\temp\pip_build_myid_OO\fann21.0.0版本，满足fann2要求

打扫干净...

我正在使用 FANN 来使用神经网络。（链接到 FANN）

我需要在训练网络后得到权重矩阵，但我没有从文档中找到任何东西。（链接到文档）

你知道怎么得到那个矩阵吗？？？

谢谢！

I am training an artificial neural network in C++ using FANN library. I cannot understand/translate the syntax used to save neurons' weights in a text file through the function "fann_save()", in particular at section connections (connected_to_neuron, weight)= (the last one in the file).

What are the values printed referring to?

我目前正在试验 FANN 的 python 绑定，下面的文章对我很有帮助：

http://jansipke.nl/using-fann-with-python/

这种方法困扰我的一件事是，调用 train_on_file 方法会导致将报告打印到标准输出。相反，我更喜欢返回值或异常处理之类的东西，所以我的 python 代码可以知道结果。我正在考虑将 pyfann 嵌入到 python 程序中，但为了实现这一点，我必须找到一种方法让它报告给 python，而不是我。不过，我在文档中找不到对此的任何引用。有什么想法吗？

我正在使用带有给定代码的 FANN 库。

我预计第一次运行的结果是 0.5，因为根据训练，输入值 0.0 的输出值应该是 0.5。因此，我预计第二次运行的输出为 0.0。

但是这两次运行的结果都是恒定的 0.0。

我在这里想念什么？

我正在尝试在 rails 项目中使用 FANN（快速人工神经网络）库。因此，我安装了风扇（安装似乎没问题，我按照网上的一些指南进行了安装）。此外，我已将ruby-fanngem 添加到我的 Gemfile 并已安装。但是，当我运行rspec以测试我的代码时，我得到一个很长的错误，其开头如下：

以及以下结局：

网上的代码/app/models/neural_network.rb:12是

I am using the FANN Library to build neural networks to proceed a regression problem. The thing is, once the networks has been trained on the relevant training set (which seems to work quite well), every single test output the exact same output. In other words, given any state of my 16 predictive variables, my predicted output, according the the ANN, is the same.

My guess would be that the network is correctly computing the first line of the calculation, then always outputs this result on other calculations, no matter what I feed it (as it seems to do very well on the first training example, giving an accurate prediction).

For instance, my first training example variables are:

My target output is 14.5, and on each test, the network outputs something between 14.69 and 14.7 (due to small calculation times and as I am only playing with the package, I train it each time I run the code). So, this output seems completely legitimate with that set of data.

The thing is, when I try to run it on several other inputs, I always get that same 14.69/14.7 (identical output on even the smallest digit).

Since the network seems to be correctly processing the training example, learning the relationship and calculatting correctly on ONE new test example, I tend to believe that all the training part is correct. Since there is no reason the network would always output the same value, my guess is that my way of testing it is not correct.

My question is: what is the exact syntax to test a FANN neural network on a new dataset? and, how do I print/save the corresponding outputs?

Here is the current state of my code:

Where:

• rowHasNA is a custom function I used to determine whether my example has at least one NA
• ann is a fann* which has already been trained
• timeSerie is a matrix<double> where each line is a test example

I am still a bit confused on how the FANN package works, since I have found no really clear documentation on how to train networks and test them. I struggle to understand how the fann_type works.

Thank you in advance.

我是使用 java 的新手。我想知道在java中使用FANN-1.1工具库来训练一组数据的必要条件和过程。

https://code.google.com/p/fannj/中给出的代码是

这里 /path/to/file 是什么