You signed in with another tab or window.Reload to refresh your session.You signed out in another tab or window.Reload to refresh your session.You switched accounts on another tab or window.Reload to refresh your session.Dismiss alert
$ python main.py --helpusage: main.py [-h] [--method-names METHOD_NAMES [METHOD_NAMES ...]] [--mode {ops_params,fps,gpu_mem} [{ops_params,fps,gpu_mem} ...]]A simple toolkitfor counting the FLOPs/MACs, Parameters, FPS and GPU Memory of the model.optional arguments:-h, --help show thishelp message andexit --method-names METHOD_NAMES [METHOD_NAMES ...] The names of the methods you want to evaluate. --mode {ops_params,fps,gpu_mem} [{ops_params,fps,gpu_mem} ...]
[New & Important] Update the library for count FLOPs/MACS frompytorch-OpCounter tofvcore which can count FLOPs/MACs of the complex module, like Transformer.
Remove the uselesstest folder.
[Experimental Feature] Add the new feature for counting the peak inference GPU memory of the model.
2022-03-03: Add more methods, add the gpu warmup process in counting FPS and update the readme.
2021-09-29: Refactor again.
2021-08-31: Refactor.
2021-08-29: Create a new repository and upload the code.
@misc{MethodsCmp,author = {Youwei Pang},title = {MethodsCmp: A Simple Toolkit for Counting the FLOPs/MACs, Parameters and FPS of Pytorch-based Methods},howpublished = {\url{https://github.com/lartpang/MethodsCmp}},year = {2021}}
About
MethodsCmp: A Simple Toolkit for Counting the FLOPs/MACs, Parameters and FPS of Pytorch-based Methods