liblinear icon indicating copy to clipboard operation
liblinear copied to clipboard

LIBLINEAR -- A Library for Large Linear Classification

Results 45 liblinear issues
Sort by recently updated
recently updated
newest added

This adds a target to make a statically compiled `liblinear.a`. This is an updated https://github.com/cjlin1/liblinear/pull/30

When I compile liblinear in Windows 10 with VS2019, I get the following error: D:\liblinear-2.30>nmake -f Makefile.win lib Microsoft (R) 程序维护实用工具 14.26.28805.0 版 版权所有 (C) Microsoft Corporation。 保留所有权利。 cl.exe /nologo...

I am using a java version of liblinear which was autogenerated from the C++ code, so I am a little conflicted about where to ask this question, so I figured...

I am one of the mac user. However, when I typed make, this error occurred clang: warning: no such sysroot directory: '/Library/Developer/CommandLineTools/SDKs/MacOSX10.15.sdk' [-Wmissing-sysroot] libsvmread.c:1:10: fatal error: 'stdio.h' file not found...

Hi there, I am wondering how I can get the intermediate alpha(a) when solving dual logistic regression, with L2 regularizer for example. ![image](https://user-images.githubusercontent.com/8280272/54477025-ae3e4700-483e-11e9-89ff-5a88a86aeff5.png) I am using Python interface but it...

This PR adds an output of `liblinear.a` to `make lib` for those of us creating statically-linked binaries.

The first commit performs some cleanup, in that it reduces the scope of some local variables for the newton step. The second commit replaces manually allocated/deallocated buffers with `std::vector` for...

Why is it that after the training, a lot of iteration information is output, but according to the example, only one should be output. When I execute `train(x, y)`, a...

Hi. This patch aims to prevent memory leaks in the situation of out of memory. It is done by eliminating alloc/free pairs with single CBuffer object, which deletes corresponding memory...

With -n option added when executing train, It would normalize every instance so it become unit length in Euclidean norm. And the .model file would have a line of "normalization...