Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details

All Projects → lucidrains → uniformer-pytorch

lucidrains / uniformer-pytorch

Licence: MIT license

Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, debuted in ICLR 2022

Programming Languages

139335 projects - #7 most used programming language

Labels

deep-learning transformers artificial-intelligence attention-mechanism video-classification 3d-convolutional-network

Projects that are alternatives of or similar to uniformer-pytorch

Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification

Stars: ✭ 109 (+21.11%)

Mutual labels: transformers, attention-mechanism, video-classification

keras-deep-learning

Various implementations and projects on CNN, RNN, LSTM, GAN, etc

Stars: ✭ 22 (-75.56%)

Mutual labels: attention-mechanism, video-classification

long-short-transformer

Implementation of Long-Short Transformer, combining local and global inductive biases for attention over long sequences, in Pytorch

Stars: ✭ 103 (+14.44%)

Mutual labels: transformers, attention-mechanism

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

Stars: ✭ 473 (+425.56%)

Mutual labels: transformers, attention-mechanism

Implementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch

Stars: ✭ 347 (+285.56%)

Mutual labels: transformers, attention-mechanism

Implementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GanFormer and TransGan paper

Stars: ✭ 137 (+52.22%)

Mutual labels: transformers, attention-mechanism

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Stars: ✭ 7,199 (+7898.89%)

Mutual labels: transformers, attention-mechanism

Reformer Pytorch

Reformer, the efficient Transformer, in Pytorch

Stars: ✭ 1,644 (+1726.67%)

Mutual labels: transformers, attention-mechanism

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Stars: ✭ 3,661 (+3967.78%)

Mutual labels: transformers, attention-mechanism

Action recognition with C3D network implemented in tensorflow

Stars: ✭ 34 (-62.22%)

Mutual labels: video-classification

A Comparison of LSTMs and Attention Mechanisms for Forecasting Financial Time Series

Stars: ✭ 53 (-41.11%)

Mutual labels: attention-mechanism

Visual-Attention-Model

Chainer implementation of Deepmind's Visual Attention Model paper

Stars: ✭ 27 (-70%)

Mutual labels: attention-mechanism

Transformer based translation quality estimation

Stars: ✭ 85 (-5.56%)

Mutual labels: transformers

organic-chemistry-reaction-prediction-using-NMT

organic chemistry reaction prediction using NMT with Attention

Stars: ✭ 30 (-66.67%)

Mutual labels: attention-mechanism

MiCT-Net-PyTorch

Video Recognition using Mixed Convolutional Tube (MiCT) on PyTorch with a ResNet backbone

Stars: ✭ 48 (-46.67%)

Mutual labels: video-classification

conv3d-video-action-recognition

My experimentation around action recognition in videos. Contains Keras implementation for C3D network based on original paper "Learning Spatiotemporal Features with 3D Convolutional Networks", Tran et al. and it includes video processing pipelines coded using mPyPl package. Model is being benchmarked on popular UCF101 dataset and achieves result…

Stars: ✭ 50 (-44.44%)

Mutual labels: video-classification

memory-compressed-attention

Implementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizing Long Sequences"

Stars: ✭ 47 (-47.78%)

Mutual labels: attention-mechanism

MinkLocMultimodal

MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition

Stars: ✭ 65 (-27.78%)

Mutual labels: 3d-convolutional-network

CLIP (Contrastive Language–Image Pre-training) for Italian

Stars: ✭ 113 (+25.56%)

Mutual labels: transformers

Using Transformers from HuggingFace in R

Stars: ✭ 66 (-26.67%)

Mutual labels: transformers

View All Similar Projects ➔

Uniformer - Pytorch

Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks

Install

$ pip install uniformer-pytorch

Usage

Uniformer-S

import torch
from uniformer_pytorch import Uniformer

model = Uniformer(
    num_classes = 1000,                 # number of output classes
    dims = (64, 128, 256, 512),         # feature dimensions per stage (4 stages)
    depths = (3, 4, 8, 3),              # depth at each stage
    mhsa_types = ('l', 'l', 'g', 'g')   # aggregation type at each stage, 'l' stands for local, 'g' stands for global
)

video = torch.randn(1, 3, 8, 224, 224)  # (batch, channels, time, height, width)

logits = model(video) # (1, 1000)

Uniformer-B

import torch
from uniformer_pytorch import Uniformer

model = Uniformer(
    num_classes = 1000
    depths = (5, 8, 20, 7)
)

Citations

@inproceedings{anonymous2022uniformer,
    title   = {UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning},
    author  = {Anonymous},
    booktitle = {Submitted to The Tenth International Conference on Learning Representations },
    year    = {2022},
    url     = {https://openreview.net/forum?id=nBU_u6DLvoK},
    note    = {under review}
}

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].

Stars: ✭ 90

Visit Git Page 🔗Visit User Page 🔗Visit Issues Page (1) 🔗