calflops
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.
Activity
- Latest release
- 2y ago
- Total releases
- 19
- Cadence
- ~daily
- Last 12 months
- 0
Details
- License
- custom
- First release
- Aug 21, 2023
Releases
| Version | Released | |
|---|---|---|
0.3.2
patch
| ||
0.3.1
patch
| ||
0.3.0
minor
| ||
0.2.9
patch
| ||
0.2.8
patch
| ||
0.2.7
patch
| ||
0.2.6
patch
| ||
0.2.5
patch
| ||
0.2.0
minor
| ||
0.1.0
minor
| ||
0.0.9
patch
| ||
0.0.8
patch
| ||
0.0.7
patch
| ||
0.0.6
patch
| ||
0.0.5
patch
| ||
0.0.4
patch
| ||
0.0.3
patch
| ||
0.0.2
patch
| ||
0.0.1
initial
|