I want to install Faiss-GPU on Lambda Stack by conda install -c pytorch faiss-gpu
but there is no conda installed.
I tried the solution mentioned here: Installing faiss on Google Colaboratory with this version of faiss https://anaconda.org/pytorch/faiss-gpu/1.6.0/download/linux-64/faiss-gpu-1.6.0-py36h1a5d453_0.tar.bz2 but is says:
ImportError: libmkl_intel_lp64.so: cannot open shared object file: No such file or directory
ModuleNotFoundError: No module named '_swigfaiss_avx2'
ImportError: libmkl_intel_lp64.so: cannot open shared object file: No such file or directory
ModuleNotFoundError: No module named '_swigfaiss'
What is the correct way to install Faiss on Lambda Stack?
The recommended way to install Faiss is through conda. Stable releases are pushed regularly to the pytorch conda channel, as well as pre-release nightly builds. The CPU-only faiss-cpu conda package is currently available on Linux, OSX, and Windows.
if you are colab just try the following:
!sudo apt-get install libomp-dev
Then it works.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With