Stars
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (Vβ¦
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Datasets, Transforms and Models specific to Computer Vision
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Always know what to expect from your data.
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
A python library for user-friendly forecasting and anomaly detection on time series.
Model interpretability and understanding for PyTorch
π A curated list of awesome MLOps tools
TextAttack π is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
Image to prompt with BLIP and CLIP
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
Awesome resources on normalizing flows.
A toolbox to iNNvestigate neural networks' predictions!
Ready-to-use code and tutorial notebooks to boost your way into few-shot learning for image classification.
SOTA Semantic Segmentation Models in PyTorch
scikit-learn cross validators for iterative stratification of multilabel data
A machine learning package for streaming data in Python. The other ancestor of River.
π Xplique is a Neural Networks Explainability Toolbox
Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch
Create SSH tunel to a running colab notebook
PyTorch samplers that output roughly balanced batches with support for multilabel datasets
Some code I wrote in Python (with tests!) to practice for Big N Interviews
Ikamoun / televit_xai
Forked from Orion-AI-Lab/televitTeleconnection-driven vision transformers for improved long-term forecasting