Recent Posts by Pragati
How to check and change the default device to MPS in PyTorch
This post will talk about GPU-accelerated PyTorch training using the MPS backend on Mac platforms. MPS enables high-performance training on GPU for MacOS devices with a Metal programming framework. I’ll also provide an overview of the software stack. So let’s talk briefly about the MPS backend and software components it relies on.
Install PyTorch 2.0 GPU/MPS for Mac M1/M2 with Conda
In this post we are going to use Miniconda, it’s a Python environment and it has a lot of scientific packages available for data science. I use Miniconda rather than Anaconda they’re both from the same company but Miniconda does not install a whole plethora of additional packages.
Difference between torch.nn.Dropout vs nn.functional.dropout in PyTorch
The modules (nn.Module) use internally the functional API. There is no difference as long as you store the parameters somewhere (manually if you prefer the functional API or in an nn.Module “automatically”)