xiaolai-sqlai/mobilenetv3
mobilenetv3 with pytorch,provide pre-train 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: 2670
- days_rel: n/a
- days_push: 1224
- n_releases_24m: 0
Adoption not part of the score
1864 stars · 345 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
A PyTorch implementation of the MobileNetV3 architecture with retrained pre-trained weights that outperform the original paper and torchvision baselines. It includes training code, pre-trained checkpoints, and training logs for ImageNet classification.
Use cases
- use mobilenetv3 pretrained weights in pytorch
- train mobilenetv3 on imagenet
- lightweight image classification model for mobile
- reproduce mobilenetv3 training results
- fine-tune a small efficient image classifier
When to choose
- you need MobileNetV3 in PyTorch with strong pre-trained weights
- you want training code to reproduce or fine-tune the model
- you need an efficient classifier for edge or mobile deployment
When to avoid
- you need other architectures or TensorFlow implementations
- you want a maintained general-purpose vision model zoo (use timm or torchvision)
- you need inference-only deployment tooling
Facets
library · maturity maintenance
machine-learning deep-learning image-processing deep-learning computer-vision image-processing python mobilenetv3 pytorch pretrained-models image-classification computer-vision gpu
1 source
- readme: https://github.com/xiaolai-sqlai/mobilenetv3 · fetched 2026-08-28 · 6f243e3177a9
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| xiaolai-sqlai/mobilenetv3 | main | 32 |
For agents
markdown · JSON · MCP: product_card(name="xiaolai-sqlai/mobilenetv3")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem