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
SGPT: Multi-billion parameter models for semantic search

SGPT: Multi-billion parameter models for semantic search This repository contains code, results and pre-trained models for the paper SGPT: Multi-billi

Niklas Muennighoff 182 Dec 29, 2022
Highly comparative time-series analysis

〰️ hctsa 〰️ : highly comparative time-series analysis hctsa is a software package for running highly comparative time-series analysis using Matlab (fu

Ben Fulcher 569 Dec 21, 2022
Public Code for NIPS submission SimiGrad: Fine-Grained Adaptive Batching for Large ScaleTraining using Gradient Similarity Measurement

Public code for NIPS submission "SimiGrad: Fine-Grained Adaptive Batching for Large Scale Training using Gradient Similarity Measurement" This repo co

Heyang Qin 0 Oct 13, 2021
Sum-Product Probabilistic Language

Sum-Product Probabilistic Language SPPL is a probabilistic programming language that delivers exact solutions to a broad range of probabilistic infere

MIT Probabilistic Computing Project 57 Nov 17, 2022
An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

Bottom-Up and Top-Down Attention for Visual Question Answering An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge. The

Hengyuan Hu 731 Jan 03, 2023
[CVPR'21] Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration

Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration This repository contains the implementation of our paper Locally Aware Pi

sfwang 70 Dec 19, 2022
Code for Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing(ICCV21)

NeuralGIF Code for Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing(ICCV21) We present Neural Generalized Implicit F

Garvita Tiwari 104 Nov 18, 2022
Convert scikit-learn models to PyTorch modules

sk2torch sk2torch converts scikit-learn models into PyTorch modules that can be tuned with backpropagation and even compiled as TorchScript. Problems

Alex Nichol 101 Dec 16, 2022
A simple python program that can be used to implement user authentication tokens into your program...

token-generator A simple python module that can be used by developers to implement user authentication tokens into your program... code examples creat

octo 6 Apr 18, 2022
Extracting and filtering paraphrases by bridging natural language inference and paraphrasing

nli2paraphrases Source code repository accompanying the preprint Extracting and filtering paraphrases by bridging natural language inference and parap

Matej Klemen 1 Mar 09, 2022
Cross-media Structured Common Space for Multimedia Event Extraction (ACL2020)

Cross-media Structured Common Space for Multimedia Event Extraction Table of Contents Overview Requirements Data Quickstart Citation Overview The code

Manling Li 49 Nov 21, 2022
Official PyTorch implementation of the paper "Self-Supervised Relational Reasoning for Representation Learning", NeurIPS 2020 Spotlight.

Official PyTorch implementation of the paper: "Self-Supervised Relational Reasoning for Representation Learning" (2020), Patacchiola, M., and Storkey,

Massimiliano Patacchiola 135 Jan 03, 2023
[ICCV2021] 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds

3DVG-Transformer This repository is for the ICCV 2021 paper "3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds" Our method "3DV

22 Dec 11, 2022
Async API for controlling Hue Lights

Hue API Async API for controlling Hue Lights Documentation: hue-api.nirantak.com Source: github.com/nirantak/hue-api Installation This is an async cli

Nirantak Raghav 4 Nov 16, 2022
Code for layerwise detection of linguistic anomaly paper (ACL 2021)

Layerwise Anomaly This repository contains the source code and data for our ACL 2021 paper: "How is BERT surprised? Layerwise detection of linguistic

6 Dec 07, 2022
Deep Learning Visuals contains 215 unique images divided in 23 categories

Deep Learning Visuals contains 215 unique images divided in 23 categories (some images may appear in more than one category). All the images were originally published in my book "Deep Learning with P

Daniel Voigt Godoy 1.3k Dec 28, 2022
Efficient Deep Learning Systems course

Efficient Deep Learning Systems This repository contains materials for the Efficient Deep Learning Systems course taught at the Faculty of Computer Sc

Max Ryabinin 173 Dec 29, 2022
This is an example implementation of the paper "Cross Domain Robot Imitation with Invariant Representation".

IR-GAIL This is an example implementation of the paper "Cross Domain Robot Imitation with Invariant Representation". Dependency The experiments are de

Zhao-Heng Yin 1 Jul 14, 2022
Code for the paper: Hierarchical Reinforcement Learning With Timed Subgoals, published at NeurIPS 2021

Hierarchical reinforcement learning with Timed Subgoals (HiTS) This repository contains code for reproducing experiments from our paper "Hierarchical

Autonomous Learning Group 21 Dec 03, 2022
(ICCV'21) Official PyTorch implementation of Relational Embedding for Few-Shot Classification

Relational Embedding for Few-Shot Classification (ICCV 2021) Dahyun Kang, Heeseung Kwon, Juhong Min, Minsu Cho [paper], [project hompage] We propose t

Dahyun Kang 82 Dec 24, 2022