This package is designed to compute the theoretical amount of FLOPs(floating-point operations)、MACs(multiply-add operations) and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model),including any custom models via torch.nn.function.* as long as based on the Pytorch implementation.
No known vulnerabilities in the latest version
[](/packages/calflops)
<a href="/packages/calflops"><img src="/api/badges/calflops?period=month" alt="PyPI Stats"></a>