soumyac1999
Follow
Stars
Implementation of the BoxE model from the NeurIPS 2020 paper "BoxE: A Box Embedding Model for Knowledge Base Completion". Also includes a visualization tool, BoxEViz, to show the evolution of boxes…
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
A PyTorch Library for Meta-learning Research
Google Drive Public File Downloader when Curl/Wget Fails
Hyperbolic Graph Convolutional Networks in PyTorch.
Library for Knowledge Intensive Language Tasks
A curated list of awesome self-supervised methods
A Pytorch-Lightning implementation of self-supervised algorithms
Fast and Easy Infinite Neural Networks in Python
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Cross-platform lib for process and system monitoring in Python
Official implementation of "Implicit Neural Representations with Periodic Activation Functions"
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
A collection of LaTeX templates used for research, courses, and miscellanea.
allRank is a framework for training learning-to-rank neural models based on PyTorch.
Code for paper "Hierarchical Text Classification with Reinforced Label Assignment" EMNLP 2019
Riemannian Adaptive Optimization Methods with pytorch optim
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
[AAAI 2019] Weakly-Supervised Hierarchical Text Classification
Recent Papers including Neural Symbolic Reasoning, Logical Reasoning, Visual Reasoning, planning and any other topics connecting deep learning and reasoning
A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiase…
A classified list of meta learning papers based on realm.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125