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

Last update: Oct 04, 2022

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 "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

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)

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

62 Dec 24, 2022

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

409 Jan 6, 2023

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

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

1 Dec 24, 2021

Transformer - Transformer in PyTorch

Transformer 完成进度 Embeddings and PositionalEncoding with example. MultiHeadAttent

1 Jan 6, 2022

Transformer Huffman coding - Complete Huffman coding through transformer

Transformer_Huffman_coding Complete Huffman coding through transformer 2022/2/19

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:

57 Nov 21, 2022

Comments

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?

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)

0.0.8(Oct 30, 2021)

Source code(tar.gz)
Source code(zip)
0.0.7(Aug 30, 2021)

Source code(tar.gz)
Source code(zip)
0.0.5(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)
0.0.4(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)
0.0.3(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)
0.0.2(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)
0.0.1(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)

Owner

Phil Wang

Working with Attention. It's all we need

GitHub Repository

Adversarial Learning for Semi-supervised Semantic Segmentation, BMVC 2018

Adversarial Learning for Semi-supervised Semantic Segmentation This repo is the pytorch implementation of the following paper: Adversarial Learning fo

464 Dec 19, 2022

Single Red Blood Cell Hydrodynamic Traps Via the Generative Design

Rbc-traps-generative-design - The generative design for single red clood cell hydrodynamic traps using GEFEST framework

4 Jun 16, 2022

[NeurIPS 2021] PyTorch Code for Accelerating Robotic Reinforcement Learning with Parameterized Action Primitives

Robot Action Primitives (RAPS) This repository is the official implementation of Accelerating Robotic Reinforcement Learning via Parameterized Action

55 Dec 27, 2022

Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer

Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer Paper on arXiv Public PyTorch implementation of two-stage peer-reg

38 Oct 14, 2022

A Learning-based Camera Calibration Toolbox

Learning-based Camera Calibration A Learning-based Camera Calibration Toolbox Paper The pdf file can be found here. @misc{zhang2022learningbased,

14 Dec 21, 2022

🐤 Nix-TTS: An Incredibly Lightweight End-to-End Text-to-Speech Model via Non End-to-End Distillation

🐤 Nix-TTS An Incredibly Lightweight End-to-End Text-to-Speech Model via Non End-to-End Distillation Rendi Chevi, Radityo Eko Prasojo, Alham Fikri Aji

156 Jan 09, 2023

Train a deep learning net with OpenStreetMap features and satellite imagery.

DeepOSM Classify roads and features in satellite imagery, by training neural networks with OpenStreetMap (OSM) data. DeepOSM can: Download a chunk of

1.3k Nov 24, 2022

Distance-Ratio-Based Formulation for Metric Learning

Distance-Ratio-Based Formulation for Metric Learning Environment Python3 Pytorch (http://pytorch.org/) (version 1.6.0+cu101) json tqdm Preparing datas

1 Dec 07, 2022

A framework to train language models to learn invariant representations.

Invariant Language Modeling Implementation of the training for invariant language models. Motivation Modern pretrained language models are critical co

6 Nov 16, 2022

[ICCV' 21] "Unsupervised Point Cloud Pre-training via Occlusion Completion"

OcCo: Unsupervised Point Cloud Pre-training via Occlusion Completion This repository is the official implementation of paper: "Unsupervised Point Clou

204 Dec 24, 2022

StyleMapGAN - Official PyTorch Implementation

StyleMapGAN - Official PyTorch Implementation StyleMapGAN: Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing Hyunsu Kim, Yunj

425 Dec 23, 2022

Medical Image Segmentation using Squeeze-and-Expansion Transformers

Medical Image Segmentation using Squeeze-and-Expansion Transformers Introduction This repository contains the code of the IJCAI'2021 paper 'Medical Im

172 Dec 20, 2022

This is the code related to "Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation" (ICCV 2021).

Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation This is the code relat

39 Sep 23, 2022

Simple improvement of VQVAE that allow to generate x2 sized images compared to baseline

vqvae_dwt_distiller.pytorch Simple improvement of VQVAE that allow to generate x2 sized images compared to baseline. It allows to generate 512x512 ima

25 Jul 19, 2022

Machine learning for NeuroImaging in Python

nilearn Nilearn enables approachable and versatile analyses of brain volumes. It provides statistical and machine-learning tools, with instructive doc

919 Dec 25, 2022

[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.

MiVOS (CVPR 2021) - Mask Propagation Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang [arXiv] [Paper PDF] [Project Page] [Papers with Code] This repo impleme

106 Jan 03, 2023