Learning and Building Convolutional Neural Networks using PyTorch

A collection of SOTA Image Classification Models in PyTorch

The repository collects many various multi-modal transformer architectures, including image transformer, video transformer, image-language transformer, video-language transformer and self-supervised learning models. Additionally, it also collects many useful tutorials and tools in these related domains.

[CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector

Implementation for paper MLP-Mixer: An all-MLP Architecture for Vision

(TPAMI2022) Salient Object Detection via Integrity Learning.

[ECCV 2022] Official pytorch implementation of the paper, "PointMixer: MLP-Mixer for Point Cloud Understanding"

Recent Advances in MLP-based Models (MLP is all you need!)

Unofficial PyTorch Implementation for pNLP-Mixer: an Efficient all-MLP Architecture for Language (https://arxiv.org/abs/2202.04350)

PyTorch implementation of Deep-Learning Architectures

An all MLP architecture for Computer Vision by Google (Paper Implementation)

An official implementation of CVPR 2019 paper "All You Need Is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification".

Keras implementation of mlp-mixer, ResMLP, gmlp. imagenet/imagenet21k weights reloaded.

Tensorflow implementation of MLP-Mixer based TTS

This repository hosts code for converting the original MLP Mixer models (JAX) to TensorFlow.

HomebrewNLP in Mesh-TensorFlow flavour for distributed TPU training

Repository for ''Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale''

Build Image Classification Models with PyTorch.

TensorFlow implementation of "MLP-Mixer: An all-MLP Architecture for Vision"

Implementation for paper MLP-Mixer: An all-MLP Architecture for Vision. MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs). MLP-Mixer contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with MLPs applied across patches (i.e. "mixing" spa…