Deep Learning ❤️ PyTorch
Deep Learning with PyTorch made easy 🚀 !
Here are the main design principles:
module
first', which means all previous model
s should be a simple module
now.
model
should only be related to the training stuffs. If we only want to use the fancy AI models at inference stage, module
should be all we need.module
s should be as 'native' as possible: no inheritance from base classes except nn.Module
should be the best, and previous inheritance-based features should be achieved by dependency injection.
module
s to be more torch.compile
friendly.carefree-learn
is MIT licensed, as found in the LICENSE
file.