Darknet-19 model

Pretrained on ImageNette. The Darknet-19 architecture was introduced in this paper.

Model description

The core idea of the author is to combine high throughput of a highway net with performance gains using better activations (Leaky ReLU) and batch normalization. This architecture is used as a backbone for YOLOv2.

Installation

Prerequisites

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

Latest stable release

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

pip install pylocron

or using conda:

conda install -c frgfm pylocron

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 https://github.com/frgfm/Holocron.git
pip install -e Holocron/.

Usage instructions

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

model = model_from_hf_hub("frgfm/darknet19").eval()

img = Image.open(path_to_an_image).convert("RGB")

# Preprocessing
config = model.default_cfg
transform = Compose([
    Resize(config['input_shape'][1:], interpolation=InterpolationMode.BILINEAR),
    PILToTensor(),
    ConvertImageDtype(torch.float32),
    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)

Citation

Original paper

@article{DBLP:journals/corr/RedmonF16,
  author    = {Joseph Redmon and
               Ali Farhadi},
  title     = {{YOLO9000:} Better, Faster, Stronger},
  journal   = {CoRR},
  volume    = {abs/1612.08242},
  year      = {2016},
  url       = {http://arxiv.org/abs/1612.08242},
  eprinttype = {arXiv},
  eprint    = {1612.08242},
  timestamp = {Mon, 13 Aug 2018 16:48:25 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/RedmonF16.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Source of this implementation

@software{Fernandez_Holocron_2020,
author = {Fernandez, François-Guillaume},
month = {5},
title = {{Holocron}},
url = {https://github.com/frgfm/Holocron},
year = {2020}
}