Pavel Iakubovskii

segmentation_models. Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

efficientnet. Implementation of EfficientNet model. Keras and TensorFlow Keras.

classification_models. Classification models trained on ImageNet. Keras.

ttach. Image Test Time Augmentation with PyTorch!

transformers-notebooks. Inference and fine-tuning examples for vision models from 🤗 Transformers

tta_wrapper. Test Time image Augmentation (TTA) wrapper for Keras model.

residual_attention_network. Keras implementation of Residual Attention Network

rt-pose. Real-time pose estimation pipeline with 🤗 Transformers

open-cities-challenge. First place solution for Open Cities DrivenData challenge

keras_telegram_callback. Telegram-bot callback for your Keras model

awesome-semantic-segmentation. :metal: awesome-semantic-segmentation

awesome-satellite-imagery-competitions. List of machine learning competitions for satellite imagery and remote sensing.

albumentations. fast image augmentation library and easy to use wrapper around other libraries

segmentation-models-pytorch.

qubvel.

keras-applications. Reference implementations of popular deep learning models.

resnet_152. Pretrained on ImageNet ResNet-152 model in Keras

EfficientNet-PyTorch. A PyTorch implementation of EfficientNet

keras_lr_finder. Plots the change of the loss function of a Keras model when the learning rate is exponentially increasing.

assets.

template. Template for data science project based on Docker and Jupyter server with Keras/Pytorch

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

volumentations. Library for 3D augmentations

MMdnn. MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

train_imagenet. Python

ipyvolume. 3d plotting for Python in the Jupyter notebook based on IPython widgets using WebGL

dvc-smp-test. Python

catalyst. Reproducible and fast DL & RL.

vision. Datasets, Transforms and Models specific to Computer Vision

notebooks. Notebooks using the Hugging Face libraries 🤗

omniglue. Code release for CVPR'24 submission 'OmniGlue'

blog. Public repo for HF blog posts

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

MONAI. AI Toolkit for Healthcare Imaging

tpu. Reference models and tools for Cloud TPUs.

DocRes. [CVPR 2024] DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks

accelerated_features. Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

huggingface_hub. The official Python client for the Huggingface Hub.

lightning-hydra-template. PyTorch Lightning + Hydra. A feature-rich template for rapid, scalable and reproducible ML experimentation with best practices. ⚡🔥⚡

keras. Deep Learning for humans

sentiment_analysis. MVideo hackathon test task. User`s review rating prediction