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

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

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)

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. 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

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

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

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

Transformer - Transformer in PyTorch

Transformer 完成进度 Embeddings and PositionalEncoding with example. MultiHeadAttent

Transformer Huffman coding - Complete Huffman coding through transformer

Transformer_Huffman_coding Complete Huffman coding through transformer 2022/2/19

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
RetinaFace: Deep Face Detection Library in TensorFlow for Python

RetinaFace is a deep learning based cutting-edge facial detector for Python coming with facial landmarks.

Sefik Ilkin Serengil 512 Dec 29, 2022
HomeAssitant custom integration for dyson

HomeAssistant Custom Integration for Dyson This custom integration is still under development. This is a HA custom integration for dyson. There are se

Xiaonan Shen 232 Dec 31, 2022
Single/multi view image(s) to voxel reconstruction using a recurrent neural network

3D-R2N2: 3D Recurrent Reconstruction Neural Network This repository contains the source codes for the paper Choy et al., 3D-R2N2: A Unified Approach f

Chris Choy 1.2k Dec 27, 2022
Official implementation of the article "Unsupervised JPEG Domain Adaptation For Practical Digital Forensics"

Unsupervised JPEG Domain Adaptation for Practical Digital Image Forensics @WIFS2021 (Montpellier, France) Rony Abecidan, Vincent Itier, Jeremie Boulan

Rony Abecidan 6 Jan 06, 2023
ML-based medical imaging using Azure

Disclaimer This code is provided for research and development use only. This code is not intended for use in clinical decision-making or for any other

Microsoft Azure 68 Dec 23, 2022
Build upon neural radiance fields to create a scene-specific implicit 3D semantic representation, Semantic-NeRF

Semantic-NeRF: Semantic Neural Radiance Fields Project Page | Video | Paper | Data In-Place Scene Labelling and Understanding with Implicit Scene Repr

Shuaifeng Zhi 243 Jan 07, 2023
An implementation of DeepMind's Relational Recurrent Neural Networks in PyTorch.

relational-rnn-pytorch An implementation of DeepMind's Relational Recurrent Neural Networks (Santoro et al. 2018) in PyTorch. Relational Memory Core (

Sang-gil Lee 241 Nov 18, 2022
Official PyTorch implementation of the paper "TEMOS: Generating diverse human motions from textual descriptions"

TEMOS: TExt to MOtionS Generating diverse human motions from textual descriptions Description Official PyTorch implementation of the paper "TEMOS: Gen

Mathis Petrovich 187 Dec 27, 2022
Rapid experimentation and scaling of deep learning models on molecular and crystal graphs.

LitMatter A template for rapid experimentation and scaling deep learning models on molecular and crystal graphs. How to use Clone this repository and

Nathan Frey 32 Dec 06, 2022
Calling Julia from Python - an experiment on data loading

Calling Julia from Python - an experiment on data loading See the slides. TLDR After reading Patrick's blog post, we decided to try to replace C++ wit

Abel Siqueira 8 Jun 07, 2022
Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing

Notice: Support for Python 3.6 will be dropped in v.0.2.1, please plan accordingly! Efficient and Scalable Physics-Informed Deep Learning Collocation-

tensordiffeq 74 Dec 09, 2022
Code repository for "Stable View Synthesis".

Stable View Synthesis Code repository for "Stable View Synthesis". Setup Install the following Python packages in your Python environment - numpy (1.1

Intelligent Systems Lab Org 195 Dec 24, 2022
Data & Code for ACCENTOR Adding Chit-Chat to Enhance Task-Oriented Dialogues

ACCENTOR: Adding Chit-Chat to Enhance Task-Oriented Dialogues Overview ACCENTOR consists of the human-annotated chit-chat additions to the 23.8K dialo

Facebook Research 69 Dec 29, 2022
BLEURT is a metric for Natural Language Generation based on transfer learning.

BLEURT: a Transfer Learning-Based Metric for Natural Language Generation BLEURT is an evaluation metric for Natural Language Generation. It takes a pa

Google Research 492 Jan 05, 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
Implementation for NeurIPS 2021 Submission: SparseFed

READ THIS FIRST This repo is an anonymized version of an existing repository of GitHub, for the AIStats 2021 submission: SparseFed: Mitigating Model P

2 Jun 15, 2022
Software Platform for solving and manipulating multiparametric programs in Python

PPOPT Python Parametric OPtimization Toolbox (PPOPT) is a software platform for solving and manipulating multiparametric programs in Python. This pack

10 Sep 13, 2022
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models Code accompanying CVPR'20 paper of the same title. Paper lin

Alex Damian 7k Dec 30, 2022
License Plate Detection Application

LicensePlate_Project 🚗 🚙 [Project] 2021.02 ~ 2021.09 License Plate Detection Application Overview 1. 데이터 수집 및 라벨링 차량 번호판 이미지를 직접 수집하여 각 이미지에 대해 '번호판

4 Oct 10, 2022
TLDR: Twin Learning for Dimensionality Reduction

TLDR (Twin Learning for Dimensionality Reduction) is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self

NAVER 105 Dec 28, 2022