Implementation of Feedback Transformer in Pytorch

Related tags

Deep Learningdeep-learningmemorytransformerattention-mechanismartifiical-intelligence
Overview

Feedback Transformer - Pytorch

Simple implementation of Feedback Transformer in Pytorch. They improve on Transformer-XL by having each token have access to the representations of all previous layers through time. This is achieved by aggregating the outputs of all layers into a shared memory, which each token across layers can attend to at each time step.

The main drawback is longer training time, due to its non-parallel nature. But I thought I'd build it to further exploration and research into this line of work.

Yannic Kilcher video

I also took the liberty to add some various enhancements, including pre-normalization, GLU gated feedforwards, as well as simplified T5 relative positional embeddings.

Install

$ pip install feedback-transformer-pytorch

Usage

import torch
from feedback_transformer_pytorch import FeedbackTransformer

model = FeedbackTransformer(
    num_tokens = 20000,           # number of tokens
    dim = 512,                    # dimension
    depth = 6,                    # depth
    seq_len = 2,                  # the sequence length of each segment or window
    mem_len = 256,                # length of the memory buffer
    dim_head = 64,                # dimension of each head
    heads = 8,                    # number of heads
    attn_dropout = 0.1,           # attention dropout
    ff_dropout = 0.1              # feedforward dropout
).cuda()

x = torch.randint(0, 20000, (2, 64)).cuda()
model(x)  # (2, 64, 20000)

If you would like to have fine control over the memory (when to detach, etc), you can do it with some extra keyword arguments on .forward

import torch
from feedback_transformer_pytorch import FeedbackTransformer

model = FeedbackTransformer(
    num_tokens = 20000,
    dim = 512,
    depth = 6,
    seq_len = 32,
    mem_len = 256
).cuda()

x1 = torch.randint(0, 20000, (2, 32)).cuda()
x2 = torch.randint(0, 20000, (2, 32)).cuda()
x3 = torch.randint(0, 20000, (2, 32)).cuda()

out1, mem1 = model(x1, return_memory = True)
out2, mem2 = model(x2, memory = mem1, return_memory = True)
out3, mem3 = model(x3, memory = mem2, return_memory = True)  # (2, 32, 20000)

Citations

@misc{fan2021addressing,
    title   = {Addressing Some Limitations of Transformers with Feedback Memory}, 
    author  = {Angela Fan and Thibaut Lavril and Edouard Grave and Armand Joulin and Sainbayar Sukhbaatar},
    year    = {2021},
    eprint  = {2002.09402},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG}
}
Comments
  • Should it really be using lower layers output for keys and values?

    Should it really be using lower layers output for keys and values?

    Could you explain the logic of how the key-value pairs are formed at these lines and whether it is necessary?

    https://github.com/lucidrains/feedback-transformer-pytorch/blob/d7d8939910d1491f01a3d93ce81d4663925fb389/feedback_transformer_pytorch/feedback_transformer_pytorch.py#L146-L151

    It looks to me that line 146 transforms the output of the layer below (x) to keys and values, and the following lines combine these keys and values with the memory. I thought that x should only be used for forming the query here, and only the existing memory is used for keys and values.

    opened by tarvaina 6
  • In place operation with gradient

    In place operation with gradient

    https://github.com/lucidrains/feedback-transformer-pytorch/blob/main/feedback_transformer_pytorch/feedback_transformer_pytorch.py#L173 I think this is an error.

    opened by hadaev8 4
  • Bug in weighted sum

    Bug in weighted sum

    Bug in https://github.com/lucidrains/feedback-transformer-pytorch/blob/main/feedback_transformer_pytorch/feedback_transformer_pytorch.py#L264

    Should be layer_weight = rearrange(layer_weight, 'd -> d () () ()')

    opened by Victor0118 1
  • Input/Output dimensions

    Input/Output dimensions

    Hey @lucidrains

    Can I check the dimensions of the input and output, is it (seq_len, dim) -> (? ,dim, tokens)?

    model = FeedbackTransformer(
    num_tokens = 20000,           # number of tokens
    dim = 512,                    # dimension
    depth = 6,                    # depth
    seq_len = 2,                  # the sequence length of each segment or window
    mem_len = 256,                # length of the memory buffer
    dim_head = 64,                # dimension of each head
    heads = 8,                    # number of heads
    attn_dropout = 0.1,           # attention dropout
    ff_dropout = 0.1              # feedforward dropout
).cuda()

x = torch.randint(0, 256, (2, 512)).cuda()
model(x)  # (1, 512, 20000)
    opened by iiSeymour 1
  • Non intuitive memory usage with cross attention

    Non intuitive memory usage with cross attention

    Give simple 256 dim and 512 len tensor and memory len 16 feedback transformer uses 3.6gm memory after forward pass. With cross attention on 100 len tensor usage grows to 14gb.

    While parallel version uses 3.1gb and 3.5gb.

    Notebooks for testing https://colab.research.google.com/drive/1dRImydFn3WthOXdLYIvdf5bsqjXcmhC5?usp=sharing https://colab.research.google.com/drive/1n653j4Pz9_U7OukhTlUbomAHMvpPXwx0?usp=sharing

    opened by hadaev8 0
  • I think mask padding value should be False

    I think mask padding value should be False

    Here https://github.com/lucidrains/feedback-transformer-pytorch/blob/with-cross-attention/feedback_transformer_pytorch/feedback_transformer_pytorch.py#L181

    opened by hadaev8 0
  • ETA for the enwiki8 example

    ETA for the enwiki8 example

    Hey @lucidrains,

    Any eta on the example for auto-regressive enwiki8 example? I and others would really appreciate it as always :)

    Also, if you can provide an example for training on custom line-by-line TXT datasets, it would be absolutely fantastic.

    Thank you.

    opened by asigalov61 0
Owner
Phil Wang
Working with Attention. It's all we need.
Phil Wang
GitHub Repository
Add gui for YoloV5 using PyQt5

HEAD 更新2021.08.16 **添加图片和视频保存功能： 1.图片和视频按照当前系统时间进行命名 2.各自检测结果存放入output文件夹 3.摄像头检测的默认设备序号更改为0，减少调试报错 温馨提示： 1.项目放置在全英文路径下，防止项目报错 2.默认使用cpu进行检测，自

Ruihao Wang 65 Dec 27, 2022
LBBA-boosted WSOD

LBBA-boosted WSOD Summary Our code is based on ruotianluo/pytorch-faster-rcnn and WSCDN Sincerely thanks for your resources. Newer version of our code

Martin Dong 20 Sep 19, 2022
Portfolio analytics for quants, written in Python

QuantStats: Portfolio analytics for quants QuantStats Python library that performs portfolio profiling, allowing quants and portfolio managers to unde

Ran Aroussi 2.7k Jan 08, 2023
CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation

CDGAN CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation CDGAN Implementation in PyTorch This is the imple

Kancharagunta Kishan Babu 6 Apr 19, 2022
It's like Shape Editor in Maya but works with skeletons (transforms).

Skeleposer What is Skeleposer? Briefly, it's like Shape Editor in Maya, but works with transforms and joints. It can be used to make complex facial ri

Alexander Zagoruyko 1 Nov 11, 2022
Weakly Supervised Dense Event Captioning in Videos, i.e. generating multiple sentence descriptions for a video in a weakly-supervised manner.

WSDEC This is the official repo for our NeurIPS paper Weakly Supervised Dense Event Captioning in Videos. Description Repo directories ./: global conf

Melon(Xuguang Duan) 96 Nov 01, 2022
Deploy pytorch classification model using Flask and Streamlit

Deploy pytorch classification model using Flask and Streamlit

Ben Seo 1 Nov 17, 2021
An efficient framework for reinforcement learning.

rl: An efficient framework for reinforcement learning Requirements Introduction PPO Test Requirements name version Python =3.7 numpy =1.19 torch =1

16 Nov 30, 2022
[ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the cameras are initialized at random poses in complex scenarios (outside-in scenes, even with less texture or intense noise )

GNeRF This repository contains official code for the ICCV 2021 paper: GNeRF: GAN-based Neural Radiance Field without Posed Camera. This implementation

Quan Meng 191 Dec 26, 2022
Decentralized Reinforcment Learning: Global Decision-Making via Local Economic Transactions (ICML 2020)

Decentralized Reinforcement Learning This is the code complementing the paper Decentralized Reinforcment Learning: Global Decision-Making via Local Ec

40 Oct 30, 2022
Molecular Sets (MOSES): A benchmarking platform for molecular generation models

Molecular Sets (MOSES): A benchmarking platform for molecular generation models Deep generative models are rapidly becoming popular for the discovery

Neelesh C A 3 Oct 14, 2022
Official code for Next Check-ins Prediction via History and Friendship on Location-Based Social Networks (MDM 2018)

MUC Next Check-ins Prediction via History and Friendship on Location-Based Social Networks (MDM 2018) Performance Details for Accuracy: | Dataset

Yijun Su 3 Oct 09, 2022
Fashion Entity Classification

Fashion-Entity-Classification - Fashion-MNIST is a dataset of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grays

ADITYA SHAH 1 Jan 04, 2022
Simulation environments for the CrazyFlie quadrotor: Used for Reinforcement Learning and Sim-to-Real Transfer

Phoenix-Drone-Simulation An OpenAI Gym environment based on PyBullet for learning to control the CrazyFlie quadrotor: Can be used for Reinforcement Le

Sven Gronauer 8 Dec 07, 2022
Convolutional neural network web app trained to track our infant’s sleep schedule using our Google Nest camera.

Machine Learning Sleep Schedule Tracker What is it? Convolutional neural network web app trained to track our infant’s sleep schedule using our Google

g-parki 7 Jul 15, 2022
Implementation detail for paper "Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet"

Multi-level-colonoscopy-malignant-tissue-detection-with-adversarial-CAC-UNet Implementation detail for our paper "Multi-level colonoscopy malignant ti

CVSM Group - email: <a href=[email protected]"> 84 Nov 22, 2022
Learning to trade under the reinforcement learning framework

Trading Using Q-Learning In this project, I will present an adaptive learning model to trade a single stock under the reinforcement learning framework

Uirá Caiado 470 Nov 28, 2022
This is a classifier which basically predicts whether there is a gun law in a state or not, depending on various things like murder rates etc.

Gun-Laws-Classifier This is a classifier which basically predicts whether there is a gun law in a state or not, depending on various things like murde

Awais Saleem 1 Jan 20, 2022
Using BERT+Bi-LSTM+CRF

Chinese Medical Entity Recognition Based on BERT+Bi-LSTM+CRF Step 1 I share the dataset on my google drive, please download the whole 'CCKS_2019_Task1

Xiang WU 55 Dec 21, 2022
Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent

Narya The Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent. This repository

Paul Garnier 121 Dec 30, 2022