Lyken17/pytorch-OpCounter
Count the MACs / FLOPs of your PyTorch model. observed · 2026-08-28
Health v2 · maintenance only
32/100
- Activity 0
- Release rhythm 35
- Longevity 100
Flags: no_releases
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 3141
- days_rel: n/a
- days_push: 786
- n_releases_24m: 0
Adoption not part of the score
5078 stars · 535 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
THOP (PyTorch-OpCounter) is a Python library that counts the MACs/FLOPs and parameters of PyTorch models. It profiles arbitrary nn.Modules with support for custom operations and includes benchmarks for popular torchvision models.
Use cases
- count flops of a pytorch model
- measure macs of resnet50
- estimate model computational complexity
- count parameters in a neural network
- compare compute cost of different model architectures
- profile custom pytorch modules for flop counting
When to choose
- you need quick MACs/FLOPs and parameter counts for PyTorch models
- you want to benchmark standard torchvision architectures
- you need custom counting rules for third-party modules
When to avoid
- you need runtime latency or memory profiling rather than static op counts
- you work outside PyTorch (e.g., TensorFlow or JAX)
- you need highly accurate hardware-aware performance measurement
Facets
library · maturity maintenance
machine-learning benchmarking developer-tools deep-learning machine-learning developer-tools python pytorch flops macs model-complexity profiling
1 source
- readme: https://github.com/Lyken17/pytorch-OpCounter · fetched 2026-08-28 · 027e35d64863
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| Lyken17/pytorch-OpCounter | main | 32 |
For agents
markdown · JSON · MCP: product_card(name="Lyken17/pytorch-OpCounter")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem