mldl Goto Github PK

kaolin

A PyTorch Library for Accelerating 3D Deep Learning Research

kd_lib

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

kdep

(CVPR2022) Official PyTorch Implementation of KDEP. Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability

keras

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow.

keras-adversarial

Keras Generative Adversarial Networks

keras-applications

Reference implementations of popular deep learning models.

keras-attention-augmented-convs

Keras implementation of Attention Augmented Convolutional Neural Networks

keras-attention-mechanism

Attention mechanism Implementation for Keras.

keras-gan

Keras implementations of Generative Adversarial Networks.

keras-ncp

Code repository of the paper Neural circuit policies enabling auditable autonomy published in Nature Machine Intelligence

keras-resources

Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library

kerlym

KEras Reinforcement Learning gYM agents

kernel-activation-functions

Several implementations of the kernel-based activation functions

kernelizedmanifoldmapping-1

This is the code corresponding to our CVPR 2019 paper.

kervolution-pytorch

Pytorch Implementation of the Kernel Convolution AKA Kervolution Layer from Kervolutional Neural Networks (https://arxiv.org/pdf/1904.03955.pdf)

kesi

Knowledge distillation from Ensembles of Iterative pruning

kmeans_selfsuper

kornia-examples

kuda

Prior Knowledge Guided Unsupervised Domain Adaptation (ECCV 2022)

l2-gcn

[CVPR 2020] L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks

l2f

Source code for CVPR 2020 paper "Learning to Forget for Meta-Learning"

l2o-training-techniques

[NeurIPS 2020 Spotlight Oral] "Training Stronger Baselines for Learning to Optimize", Tianlong Chen*, Weiyi Zhang*, Jingyang Zhou, Shiyu Chang, Sijia Liu, Lisa Amini, Zhangyang Wang

lab

A customisable 3D platform for agent-based AI research

lada

Local Context-Aware Active Domain Adaptation

ladder-latent-data-distribution-modelling

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We propose LaDDer to achieve accurate modelling of the latent data distribution in a variational autoencoder framework and to facilitate better representation learning. The central idea of LaDDer is a meta-embedding concept, which uses multiple VAE models to learn an embedding of the embeddings, forming a ladder of encodings. We use a non-parametric mixture as the hyper prior for the innermost VAE and learn all the parameters in a unified variational framework. From extensive experiments, we show that our LaDDer model is able to accurately estimate complex latent distribution and results in improvement in the representation quality.

lae

A Unified Continual Learning Framework with General Parameter-Efficient Tuning, ICCV2023 [PyTorch Code]

lambda-networks

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

lambdanet

Probabilistic Type Inference using Graph Neural Networks

lambdanet-1

Purely functional artificial neural network library implemented in Haskell.

lamcts

The release codes of LA-MCTS with its application to Neural Architecture Search.