Downloads · 30 days
6
25% of all-time downloads
pilot-mobilenet_v3_large-imagenette
FasterAI-Labs/pilot-mobilenet_v3_large-imagenette
pilot-mobilenet_v3_large-imagenette is a machine learning model from FasterAI-Labs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for fastermodels. The card lists the license as bsd-3-clause.
Imagenette validation, 3925 images, one run. Every published file is scored after reload; the reference is the fine-tuned source.
All-time downloads
24
Public
Repo size
31 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt4.7 MB · 50%
At a glance
- Library
- fastermodels
- License
- bsd-3-clause
- Access
- Public
- Created
- Sep 11, 2026
- Updated
- Sep 11, 2026
- SHA
- f31b06ce
Datasets
Model card
From the Hugging Face model README
mobilenet_v3_large — Imagenette pilot
Imagenette validation, 3925 images, one run. Every published file is scored after reload; the reference is the fine-tuned source.
Criteria
Top-1 on the evaluation set named above, size on disk, peak live activations and multiply-accumulates — the last two for one image of (3, 160, 160) at batch 1 — each against the fine-tuned mobilenet_v3_large.
INT8 TorchScript — load with fastermodels.load(repo) or torch.jit.load (model.torchscript.pt)
| criterion | reference | this artifact | gap |
|---|---|---|---|
| top-1 | 96.5 % | 94.8 % | -1.7 pt [-2.3, -1.1] |
| size | 17.0 MB, 4.2 M params | 4.7 MB, n/a params | -72.6 % |
| memory | 3.3 MB | 0.5 MB | -84.4 % |
| MACs | 111.2 M | 111.2 M | +0.0 % |
INT8 ONNX — load with any ONNX runtime, scored here through onnxruntime (model.onnx)
| criterion | reference | this artifact | gap |
|---|---|---|---|
| top-1 | 96.5 % | 94.4 % | -2.1 pt [-2.7, -1.5] |
| size | 17.0 MB, 4.2 M params | 4.6 MB, n/a params | -72.9 % |
| memory | 3.3 MB | 0.5 MB | -84.4 % |
| MACs | 111.2 M | 111.2 M | +0.0 % |
Gaps are measured on the same images as the reference; brackets give the 95 % interval.
Latency
non mesurée
Provenance
- Source model: torchvision.models.mobilenet_v3_large (IMAGENET1K_V1)
- fasterai:
0.4.0 - fastermodels:
0.1.0 - torch:
2.9.1+cu128 - measured_on:
2026-09-11 - source_state_hash:
965676792fcd
Publication checks: 10/10 passed.
- Library
- fastermodels
- License
- bsd-3-clause
- Created
- Sep 11, 2026
- Updated
- Sep 11, 2026