Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper

Related tags

Deep Learningdeep-learningtransformersartificial-intelligenceadaptive-computation-time
Overview

Ponder(ing) Transformer

Implementation of a Transformer that learns to adapt the number of computational steps it takes depending on the difficulty of the input sequence, using the scheme from the PonderNet paper. Will also try to abstract out a pondering module that can be used with any block that returns an output with the halting probability.

This repository would not have been possible without repeated viewings of Yannic's educational video

Install

$ pip install ponder-transformer

Usage

import torch
from ponder_transformer import PonderTransformer

model = PonderTransformer(
    num_tokens = 20000,
    dim = 512,
    max_seq_len = 512
)

mask = torch.ones(1, 512).bool()

x = torch.randint(0, 20000, (1, 512))
y = torch.randint(0, 20000, (1, 512))

loss = model(x, labels = y, mask = mask)
loss.backward()

Now you can set the model to .eval() mode and it will terminate early when all samples of the batch have emitted a halting signal

import torch
from ponder_transformer import PonderTransformer

model = PonderTransformer(
    num_tokens = 20000,
    dim = 512,
    max_seq_len = 512,
    causal = True
)

x = torch.randint(0, 20000, (2, 512))
mask = torch.ones(2, 512).bool()

model.eval() # setting to eval makes it return the logits as well as the halting indices

logits, layer_indices = model(x,  mask = mask) # (2, 512, 20000), (2)

# layer indices will contain, for each batch element, which layer they exited

Citations

@misc{banino2021pondernet,
    title   = {PonderNet: Learning to Ponder}, 
    author  = {Andrea Banino and Jan Balaguer and Charles Blundell},
    year    = {2021},
    eprint  = {2107.05407},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG}
}
You might also like...
Implementation of the Transformer variant proposed in
Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"

FLASH - Pytorch Implementation of the Transformer variant proposed in the paper Transformer Quality in Linear Time Install $ pip install FLASH-pytorch

Phil Wang 209 Dec 28, 2022
Third party Pytorch implement of Image Processing Transformer (Pre-Trained Image Processing Transformer arXiv:2012.00364v2)

ImageProcessingTransformer Third party Pytorch implement of Image Processing Transformer (Pre-Trained Image Processing Transformer arXiv:2012.00364v2)

null 61 Jan 1, 2023
Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.
Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.

Episodic Transformers (E.T.) Episodic Transformer for Vision-and-Language Navigation Alexander Pashevich, Cordelia Schmid, Chen Sun Episodic Transform

Alex Pashevich 62 Dec 24, 2022
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped

CSWin-Transformer This repo is the official implementation of "CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows". Th

Microsoft 409 Jan 6, 2023
3D-Transformer: Molecular Representation with Transformer in 3D Space

3D-Transformer: Molecular Representation with Transformer in 3D Space

null 55 Dec 19, 2022
This repository builds a basic vision transformer from scratch so that one beginner can understand the theory of vision transformer.

vision-transformer-from-scratch This repository includes several kinds of vision transformers from scratch so that one beginner can understand the the

null 1 Dec 24, 2021
Transformer - Transformer in PyTorch

Transformer 完成进度 Embeddings and PositionalEncoding with example. MultiHeadAttent

Tianyang Li 1 Jan 6, 2022
Transformer Huffman coding - Complete Huffman coding through transformer

Transformer_Huffman_coding Complete Huffman coding through transformer 2022/2/19

null 3 May 19, 2022
The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

Codebase for training transformers on systematic generalization datasets. The official repository for our EMNLP 2021 paper The Devil is in the Detail:

Csordás Róbert 57 Nov 21, 2022
Comments
  • Evaluating ponder-net on more pondering-steps than trained on.

    Evaluating ponder-net on more pondering-steps than trained on.

    As the paper says,

    In evaluation, and under known temporal or computational limitations, N can be set naively as a constant (or not set any limit, i.e. N → ∞). For training, we found that a more effective (and interpretable) way of parameterizing N is by defining a minimum cumulative probability of halting. N is then the smallest value of n such that sum( p_sub_ j > 1 − ε)over(j=1, n) , with the hyper-parameter ε positive near 0 (in our experiments 0.05).

    from that I infer that pondering can be done to more steps than trained on. How can be done so with this implementation?

    edit: I was going through the paper again,and I think what the paper means is that the max_num_pondering_steps:N should be re evaluated at every training-step, the model should be run till the condition is met or a pre-defined num of max steps is reached, and where the cumsum_probs condition will be met will be set as 'N', with the cumsum_probs normalised with one of the methods. Then that value of 'N' will be used to calc prior geom for the kl_div (and not normalising the prior geom term).

    i.e. if the num of pondering steps are initially set to 'M', then the model will recur for 'k' steps - i.e. till the condition is met or for 'M' num of max steps; then 'N' will be calculated by first calculating the probabilities - p_0 to p_k - then normalizing through one of the methods, then calculate cumulative-sum of those probabilities, and checking where the sum is greater than threshold, and assigning it the value 'N'. After that, calculating prior geometric values with the defined hyper-parameter, for 'N' seq-len, and using this in the kl-div term against the halting probs truncated to 'N' steps.

    λp is a hyper-parameter that defines a geometric prior distribution pG(λp) on the halting policy (truncated at N)

    opened by Vbansal21 0
  • Can pondernet used for imagenet?

    Can pondernet used for imagenet?

    I plan to do a project on the complexity of tasks on image dataset like imagenet, cifar 100. If I use a vision transformer, then can I implement my project?

    opened by fryegg 2
Releases(0.0.8)
Owner
Phil Wang
Working with Attention. It's all we need
Phil Wang
GitHub Repository
Library extending Jupyter notebooks to integrate with Apache TinkerPop and RDF SPARQL.

Graph Notebook: easily query and visualize graphs The graph notebook provides an easy way to interact with graph databases using Jupyter notebooks. Us

Amazon Web Services 501 Dec 28, 2022
A CROSS-MODAL FUSION NETWORK BASED ON SELF-ATTENTION AND RESIDUAL STRUCTURE FOR MULTIMODAL EMOTION RECOGNITION

CFN-SR A CROSS-MODAL FUSION NETWORK BASED ON SELF-ATTENTION AND RESIDUAL STRUCTURE FOR MULTIMODAL EMOTION RECOGNITION The audio-video based multimodal

skeleton 15 Sep 26, 2022
Model parallel transformers in Jax and Haiku

Mesh Transformer Jax A haiku library using the new(ly documented) xmap operator in Jax for model parallelism of transformers. See enwik8_example.py fo

Ben Wang 4.8k Jan 01, 2023
Code for "Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo"

Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo This repository includes the source code for our CVPR 2021 paper on multi-view mult

Jiahao Lin 66 Jan 04, 2023
Codes and Data Processing Files for our paper.

Code Scripts and Processing Files for EEG Sleep Staging Paper 1. Folder Tree ./src_preprocess (data preprocessing files for SHHS and Sleep EDF) sleepE

Chaoqi Yang 18 Dec 12, 2022
Code for HLA-Face: Joint High-Low Adaptation for Low Light Face Detection (CVPR21)

HLA-Face: Joint High-Low Adaptation for Low Light Face Detection The official PyTorch implementation for HLA-Face: Joint High-Low Adaptation for Low L

Wenjing Wang 77 Dec 08, 2022
Educational 2D SLAM implementation based on ICP and Pose Graph

slam-playground Educational 2D SLAM implementation based on ICP and Pose Graph How to use: Use keyboard arrow keys to navigate robot. Press 'r' to vie

Kirill 19 Dec 17, 2022
The first dataset on shadow generation for the foreground object in real-world scenes.

Object-Shadow-Generation-Dataset-DESOBA Object Shadow Generation is to deal with the shadow inconsistency between the foreground object and the backgr

BCMI 105 Dec 30, 2022
Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"

BEGAN in Tensorflow Tensorflow implementation of BEGAN: Boundary Equilibrium Generative Adversarial Networks. Requirements Python 2.7 or 3.x Pillow tq

Taehoon Kim 922 Dec 21, 2022
An excellent hash algorithm combining classical sponge structure and RNN.

SHA-RNN Recurrent Neural Network with Chaotic System for Hash Functions Anonymous Authors [摘要] 在这次作业中我们提出了一种新的 Hash Function —— SHA-RNN。其以海绵结构为基础，融合了混

Houde Qian 5 May 15, 2022
Semi-supervised Video Deraining with Dynamical Rain Generator (CVPR, 2021, Pytorch)

S2VD Semi-supervised Video Deraining with Dynamical Rain Generator (CVPR, 2021) Requirements and Dependencies Ubuntu 16.04, cuda 10.0 Python 3.6.10, P

Zongsheng Yue 53 Nov 23, 2022
The dataset of tweets pulling from Twitters with keyword: Hydroxychloroquine, location: US, Time: 2020

HCQ_Tweet_Dataset: FREE to Download. Keywords: HCQ, hydroxychloroquine, tweet, twitter, COVID-19 This dataset is associated with the paper "Understand

2 Mar 16, 2022
SEC'21: Sparse Bitmap Compression for Memory-Efficient Training onthe Edge

Training Deep Learning Models on The Edge Training on the Edge enables continuous learning from new data for deployed neural networks on memory-constr

Brown University Scale Lab 4 Nov 18, 2022
Source code for paper "ATP: AMRize Than Parse! Enhancing AMR Parsing with PseudoAMRs" @NAACL-2022

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs Hi this is the source code of our paper "ATP: AMRize Then Parse! Enhancing AMR Parsing w

Chen Liang 13 Nov 23, 2022
You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors

You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors In this paper, we propose a novel local descriptor-based fra

Haiping Wang 80 Dec 15, 2022
Implementation of a protein autoregressive language model, but with autoregressive infilling objective (editing subsequences capability)

Protein GLM (wip) Implementation of a protein autoregressive language model, but with autoregressive infilling objective (editing subsequences capabil

Phil Wang 17 May 06, 2022
GRF: Learning a General Radiance Field for 3D Representation and Rendering

GRF: Learning a General Radiance Field for 3D Representation and Rendering [Paper] [Video] GRF: Learning a General Radiance Field for 3D Representatio

Alex Trevithick 243 Dec 29, 2022
Official implementation of YOGO for Point-Cloud Processing

You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module By Chenfeng Xu, Bohan Zhai, Bichen Wu, T

Chenfeng Xu 67 Dec 20, 2022
DLWP: Deep Learning Weather Prediction

DLWP: Deep Learning Weather Prediction DLWP is a Python project containing data-

Kushal Shingote 3 Aug 14, 2022
"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback"

This is code repo for our EMNLP 2017 paper "Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback", which implements the A2C algorithm on top of a neural encoder-

Khanh Nguyen 131 Oct 21, 2022