elias-ramzi

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Deep-Learning-in-Production

In this repository, I will share some useful notes and references about deploying deep learning-based models in production.

PerceptualSimilarity

LPIPS metric. pip install lpips

plotext

plotting on terminal

fastmoe

A fast MoE impl for PyTorch

solo-learn

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

lovely-tensors

Tensors, for human consumption

mixture-of-experts

PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538

Adan

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

vmoe

self-label

Self-labelling via simultaneous clustering and representation learning. (ICLR 2020)

XAI

Papers and code of Explainable AI esp. w.r.t. Image classificiation

knn-ood

Code for ICML 2022 paper "Out-of-distribution Detection with Deep Nearest Neighbors"

pytorch-graphsage

Representation learning on large graphs using stochastic graph convolutions.

HCSC

[CVPR 2022] PyTorch implementation of Hierarchical Contrastive Selective Coding (HCSC) (https://arxiv.org/abs/2202.00455)

graph-neural-networks-for-drug-discovery

STML-CVPR22

Official PyTorch Implementation of Self-Taught Metric Learning without Labels, CVPR 2022

Deformable-ProtoPNet

The official repository for Deformable ProtoPNet, as described in "Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes".

Transformer_Based_Geo-localization

This is the repository for ECCV2022 paper titled: "Where in the World is this Image? Transformer-based Geo-localization in the Wild".

Residual-Flow

An implementation of the Residual Flow algorithm for out-of-distribution detection.

insclr

cog

ImageNet-CoG is a benchmark for concept generalization. It provides a full evaluation framework for pre-trained visual representations which measure how well they generalize to unseen concepts.

UnHyperML

Code for "Unsupervised Hyperbolic Metric Learning" in CVPR 2021.

metric-learning-using-contextual-similarity

this-does-not-look-like-that

Code for the experiments of the ICML 2021 Interpretability workshop paper "This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks"

HyP2-Loss

Probabilistic_Deep_Metric_Learning

This repository contains the code for our ECCV 2022 paper on our "Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning".

scrap_paper_digest

Scrapping Highlights paper digest and display