A easy to use huggingface wrapper for computer vision.
Project description
HugsVision
HugsVision is an open-source and easy to use all-in-one huggingface wrapper for computer vision.
The goal is to create a fast, flexible and user-friendly toolkit that can be used to easily develop state-of-the-art computer vision technologies, including systems for Image Classification, Semantic Segmentation, Object Detection, Image Generation, Denoising and much more.
⚠️ HugsVision is currently in beta. ⚠️
Quick installation
HugsVision is constantly evolving. New features, tutorials, and documentation will appear over time. HugsVision can be installed via PyPI to rapidly use the standard library. Moreover, a local installation can be used by those users than want to run experiments and modify/customize the toolkit. HugsVision supports both CPU and GPU computations. For most recipes, however, a GPU is necessary during training. Please note that CUDA must be properly installed to use GPUs.
Anaconda setup
Once Anaconda is installed, you can create a new environment with:
conda create --name HugsVision python=3.6 -y
Then, activate it with:
conda activate HugsVision
Now, you can install all the needed packages!
More information on managing environments with Anaconda can be found in the conda cheat sheet.
Install via PyPI
Once you have created your Python environment (Python 3.6+) you can simply type:
pip install hugsvision
If you already have a older version:
pip install hugsvision --upgrade
Then you can access HugsVision with:
import hugsvision as vision
Install with GitHub
Once you have created your Python environment (Python 3.6+) you can simply type:
git clone https://github.com/qanastek/HugsVision.git
cd HugsVision
pip install -r requirements.txt
pip install --editable .
Then you can access HugsVision with:
import hugsvision as vision
Any modification made to the hugsvision
package will be automatically interpreted as we installed it with the --editable
flag.
Running an experiment
In HugsVision, you can run experiments in this way:
cd recipes/<DATASET>/<TASK>/
python train_example_vit.py --imgs="<PATH_TO_IMAGES_DIRECTORY>" --name="<OUTPUT_MODEL_NAME>"
python predict.py --img="<IMG_PATH>" --path="<MODEL_PATH>"
For example, we can use the Pneumothorax
dataset available on Kaggle to train a binary classification model.
Steps:
- Move to the recipe directory
cd recipes/pneumothorax/binary_classification/
- Download the dataset here ~779 MB.
- Transform the dataset into a directory based one, thanks to the
process.py
script. - Train the model
python train_example_vit.py --imgs="./pneumothorax_binary_classification_task_data/" --name="pneumo_model_vit" --epochs=1
- Rename
<MODEL_PATH>/config.json
to<MODEL_PATH>/preprocessor_config.json
in my case, the model is situated at the path./out/MYVITMODEL/1_2021-08-10-00-53-58/model/
- Make a prediction
python predict.py --img="42.png" --path="./out/MYVITMODEL/1_2021-08-10-00-53-58/model/"
Model architectures
All the model checkpoints provided by 🤗 Transformers and compatible with our tasks can be seamlessly integrated from the huggingface.co model hub where they are uploaded directly by users and organizations.
Before starting implementing, please check if your model has an implementation in PyTorch
by refering to this table.
🤗 Transformers currently provides the following architectures for Computer Vision:
- ViT (from Google Research, Brain Team) released with the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, by Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby.
- DeiT (from Facebook AI and Sorbonne University) released with the paper Training data-efficient image transformers & distillation through attention by Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou.
- DETR (from Facebook AI) released with the paper End-to-End Object Detection with Transformers by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov and Sergey Zagoruyko.
Build PyPi package
Build: python setup.py sdist bdist_wheel
Upload: twine upload dist/*
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for hugsvision-0.1.46-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e2c2dda8b50ca1bef78d5389c607bc8822c01ed223a45357246235fd7312cba8 |
|
MD5 | 33be053cf6f46a2a00d57bad418c2d23 |
|
BLAKE2b-256 | 88043c86b1d9521aade5b41bccfbde1e6eb72dfe128b2fdd177d969d10a7d701 |