search

xiaohuiyan / BTM

Code for Biterm Topic Model (published in WWW 2013)
https://github.com/xiaohuiyan/xiaohuiyan.github.io/blob/master/paper/BTM-WWW13.pdf
Apache License 2.0
405 stars 137 forks source link

./src/btm: No such file or directory #8

Closed sruteesh closed 6 years ago

sruteesh commented 8 years ago

When I run runExample.sh I am getting the following error

=============== Topic Learning ============= make: Entering directory /home/saipavan/Desktop/BTM-master/src' g++ -c -pipe -O3 model.cpp -o model.o make: g++: Command not found make: *** [model.o] Error 127 make: Leaving directory/home/saipavan/Desktop/BTM-master/src' ../src/btm est 20 28634 2.500 0.005 500 501 ../output/doc_wids.txt ../output/model/ runExample.sh: line 31: ../src/btm: No such file or directory

When I browsw through the src folder I couldn't find any file named btm. Please respond.

shachi04 commented 8 years ago

src/btm is the executable created on the 'make' command. Looks like its not able to find the g++ compiler. Try to type 'g++' and run on the terminal. If you get a 'command not found' error, then the compiler is missing. You'll need to install g++ first.

sruteesh commented 8 years ago

Thanks @shachi04. I was able to run the program. As part of my final year project, I wanted to use BTM for understanding topics of a user and his followers. But to get a single output(topics of the user) BTM is taking around 3-4 min ( I am using Ubuntu 2nd gen i5 system with 4GB RAM). This is way too long as you can imagine the time it would take to understand the topics of 1000 followers. Is there any way around. Any help is greatly appreciated. ᐧ

On Tue, Apr 12, 2016 at 2:34 AM, shachi04 notifications@github.com wrote:

src/btm is the executable created on the 'make' command. Looks like its not able to find the g++ compiler. Try to type 'g++' and run on the terminal. If you get a 'command not found' error, then the compiler is missing. You'll need to install g++ first.

— You are receiving this because you authored the thread. Reply to this email directly or view it on GitHub https://github.com/xiaohuiyan/BTM/issues/8#issuecomment-208559901

Regards, Sruteesh Kumar, 5th year Undergrad, Dept. of Engineering Design IIT Madras, Ph: 9043412821

xiaohuiyan commented 8 years ago

Hi, @sruteesh, the training time of BTM is time-consuming, but the inference of BTM is fast. You can first training BTM to learning all the topics over the whole data, and then infer each person's topics.