mobilenet_v3_small /
docs: Updated dataset reference
license: apache-2.0
  - image-classification
  - pytorch
  - onnx
  - pyronear/openfire

MobileNet V3 - Small model

Pretrained on a dataset for wildfire binary classification (soon to be shared). The MobileNet V3 architecture was introduced in this paper.

Model description

The core idea of the author is to simplify the final stage, while using SiLU as activations and making Squeeze-and-Excite blocks larger.



Python 3.6 (or higher) and pip/conda are required to install PyroVision.

Latest stable release

You can install the last stable release of the package using pypi as follows:

pip install pyrovision

or using conda:

conda install -c pyronear pyrovision

Developer mode

Alternatively, if you wish to use the latest features of the project that haven't made their way to a release yet, you can install the package from source (install Git first):

git clone
pip install -e pyro-vision/.

Usage instructions

from PIL import Image
from torchvision.transforms import Compose, ConvertImageDtype, Normalize, PILToTensor, Resize
from torchvision.transforms.functional import InterpolationMode
from pyrovision.models import model_from_hf_hub

model = model_from_hf_hub("pyronear/mobilenet_v3_small").eval()

img ="RGB")

# Preprocessing
config = model.default_cfg
transform = Compose([
    Resize(config['input_shape'][1:], interpolation=InterpolationMode.BILINEAR),
    Normalize(config['mean'], config['std'])

input_tensor = transform(img).unsqueeze(0)

# Inference
with torch.inference_mode():
    output = model(input_tensor)
probs = output.squeeze(0).softmax(dim=0)


Original paper

  author    = {Andrew Howard and
               Mark Sandler and
               Grace Chu and
               Liang{-}Chieh Chen and
               Bo Chen and
               Mingxing Tan and
               Weijun Wang and
               Yukun Zhu and
               Ruoming Pang and
               Vijay Vasudevan and
               Quoc V. Le and
               Hartwig Adam},
  title     = {Searching for MobileNetV3},
  journal   = {CoRR},
  volume    = {abs/1905.02244},
  year      = {2019},
  url       = {},
  eprinttype = {arXiv},
  eprint    = {1905.02244},
  timestamp = {Thu, 27 May 2021 16:20:51 +0200},
  biburl    = {},
  bibsource = {dblp computer science bibliography,}

Source of this implementation

author = {Chintala, Soumith},
month = {4},
title = {{Torchvision}},
url = {},
year = {2017}