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
PClean: A Domain-Specific Probabilistic Programming Language for Bayesian Data Cleaning

PClean: A Domain-Specific Probabilistic Programming Language for Bayesian Data Cleaning Warning: This is a rapidly evolving research prototype.

MIT Probabilistic Computing Project 190 Dec 27, 2022
Code for Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions

EMS-COLS-recourse Initial Code for Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions Folder structure: data folder contains raw an

Prateek Yadav 1 Nov 25, 2022
Notebooks for my "Deep Learning with TensorFlow 2 and Keras" course

Deep Learning with TensorFlow 2 and Keras – Notebooks This project accompanies my Deep Learning with TensorFlow 2 and Keras trainings. It contains the

Aurélien Geron 1.9k Dec 15, 2022
Official PyTorch implementation of StyleGAN3

Modified StyleGAN3 Repo Changes Made tied to python 3.7 syntax .jpgs instead of .pngs for training sample seeds to recreate the 1024 training grid wit

Derrick Schultz (he/him) 83 Dec 15, 2022
Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

Dataset Distillation by Matching Training Trajectories Project Page | Paper This repo contains code for training expert trajectories and distilling sy

George Cazenavette 256 Jan 05, 2023
Lightweight mmm - Lightweight (Bayesian) Media Mix Model

Lightweight (Bayesian) Media Mix Model This is not an official Google product. L

Google 342 Jan 03, 2023
Code for Emergent Translation in Multi-Agent Communication

Emergent Translation in Multi-Agent Communication PyTorch implementation of the models described in the paper Emergent Translation in Multi-Agent Comm

Facebook Research 75 Jul 15, 2022
The dataset and source code for our paper: "Did You Ask a Good Question? A Cross-Domain Question IntentionClassification Benchmark for Text-to-SQL"

TriageSQL The dataset and source code for our paper: "Did You Ask a Good Question? A Cross-Domain Question Intention Classification Benchmark for Text

Yusen Zhang 22 Nov 09, 2022
Boston House Prediction Valuation Tool

Boston-House-Prediction-Valuation-Tool From Below Anlaysis The Valuation Tool is Designed Correlation Matrix Regrssion Analysis Between Target Vs Pred

0 Sep 09, 2022
The official re-implementation of the Neurips 2021 paper, "Targeted Neural Dynamical Modeling".

Targeted Neural Dynamical Modeling Note: This is a re-implementation (in Tensorflow2) of the original TNDM model. We do not plan to further update the

6 Oct 05, 2022
SLAMP: Stochastic Latent Appearance and Motion Prediction

SLAMP: Stochastic Latent Appearance and Motion Prediction Official implementation of the paper SLAMP: Stochastic Latent Appearance and Motion Predicti

Kaan Akan 34 Dec 08, 2022
Image Restoration Using Swin Transformer for VapourSynth

SwinIR SwinIR function for VapourSynth, based on https://github.com/JingyunLiang/SwinIR. Dependencies NumPy PyTorch, preferably with CUDA. Note that t

Holy Wu 11 Jun 19, 2022
Official implementation of the paper 'Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution' in CVPR 2022

LDL Paper | Supplementary Material Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution Jie Liang*, Hu

150 Dec 26, 2022
Norm-based Analysis of Transformer

Norm-based Analysis of Transformer Implementations for 2 papers introducing to analyze Transformers using vector norms: Kobayashi+'20 Attention is Not

Goro Kobayashi 52 Dec 05, 2022
PyTorch implementation of the YOLO (You Only Look Once) v2

PyTorch implementation of the YOLO (You Only Look Once) v2 The YOLOv2 is one of the most popular one-stage object detector. This project adopts PyTorc

申瑞珉 (Ruimin Shen) 433 Nov 24, 2022
Prototypical Networks for Few shot Learning in PyTorch

Prototypical Networks for Few shot Learning in PyTorch Simple alternative Implementation of Prototypical Networks for Few Shot Learning (paper, code)

Orobix 835 Jan 08, 2023
All supplementary material used by me while TA-ing CS3244: Machine Learning

CS3244-Tutorial-Material All supplementary material used by me while TA-ing CS3244: Machine Learning at NUS School of Computing. What is this? I teach

Rishabh Anand 18 Sep 23, 2022
Activity image-based video retrieval

Cross-modal-retrieval Our approach is focus on Activity Image-to-Video Retrieval (AIVR) task. The compared methods are state-of-the-art single modalit

BCMI 75 Oct 21, 2021
Code for the paper: Sketch Your Own GAN

Sketch Your Own GAN Project | Paper | Youtube | Slides Our method takes in one or a few hand-drawn sketches and customizes an off-the-shelf GAN to mat

677 Dec 28, 2022
Allows including an action inside another action (by preprocessing the Yaml file). This is how composite actions should have worked.

actions-includes Allows including an action inside another action (by preprocessing the Yaml file). Instead of using uses or run in your action step,

Tim Ansell 70 Nov 04, 2022