{"library":"ultralytics-thop","type":"library","category":null,"description":"Ultralytics THOP is a Python library for fast computation of PyTorch model Multiply-Accumulate Operations (MACs) and parameters. It is based on the original `thop` project, maintained by Ultralytics, and provides a robust tool for analyzing the computational cost of deep learning models. The current version is 2.0.18, with a maintenance-focused release cadence.","language":"python","status":"active","version":"2.0.18","tags":["pytorch","model profiling","flops","macs","performance","deep learning"],"last_verified":"Wed May 20","install":[{"cmd":"pip install ultralytics-thop","imports":["from thop import profile","from thop import clever_format","from thop import profile_origin"]}],"homepage":"https://ultralytics.com","github":"https://github.com/ultralytics/thop","docs":"https://docs.ultralytics.com","changelog":"https://github.com/ultralytics/thop/releases","pypi":"https://pypi.org/project/ultralytics-thop/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":20,"avg_install_s":67.6,"avg_import_s":5.47,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/ultralytics-thop/compatibility"}}