Installation instructions are provided for linux and under conda enviroment. We recomend to create a new conda environment for this installation.
P2PaLA is implemented in PyTorch, and depends on the following:
Note that currently we only support GPU. You need to use NVIDIA's cuDNN library. Register first for the CUDA Developer Program (it's free) and download the library from NVIDIA's website.
This code is tested only on Python2.7, Python3. should work but untested.
Once PyTorch is installed the following libs are required:
- tensorboard-pytorch (v0.9).
- OpenCv (3.1.0).
Then execute:
git clone https://github.com/lquirosd/P2PaLA.git