swa
swa copied to clipboard
Stochastic Weight Averaging in PyTorch
Hi, can you update the code for plotting Figure 3 in the paper?
Hi! I am trying to implement SWA with Torchbearer but I'm having issues with the state etc. Could anybody point me in the direction of some resources to better understand...
In case of distributed training, e.g. DDP, each gpu will only process a minibatch, and the bn statistics computed in each gpu are different. When SWA is adopted, we need...
Hi, just noticed this wonderful work. I have made this code available for latest PyTorch version by providing minor revisions. Please consider merging.
I see def conv_init(m): in the wide_resnet.py of models, but it just be defined, and it's not applyed. Is it should be used as net.apply(conv_init)?
# Set Up Python Testing Infrastructure ## Summary This PR establishes a complete testing infrastructure for the PyTorch SWA-Gaussian project using Poetry as the package manager and pytest as the...