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
Codebase for testing whether hidden states of neural networks encode discrete structures.

structural-probes Codebase for testing whether hidden states of neural networks encode discrete structures. Based on the paper A Structural Probe for

John Hewitt 349 Dec 17, 2022
Image Lowpoly based on Centroid Voronoi Diagram via python-opencv and taichi

CVTLowpoly: Image Lowpoly via Centroid Voronoi Diagram Image Sharp Feature Extraction using Guide Filter's Local Linear Theory via opencv-python. The

Pupa 4 Jul 29, 2022
Benchmarks for semi-supervised domain generalization.

Semi-Supervised Domain Generalization This code is the official implementation of the following paper: Semi-Supervised Domain Generalization with Stoc

Kaiyang 49 Dec 10, 2022
Alternatives to Deep Neural Networks for Function Approximations in Finance

Alternatives to Deep Neural Networks for Function Approximations in Finance Code companion repo Overview This is a repository of Python code to go wit

15 Dec 17, 2022
Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)

Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic

NAVER/LINE Vision 30 Dec 06, 2022
AutoML library for deep learning

Official Website: autokeras.com AutoKeras: An AutoML system based on Keras. It is developed by DATA Lab at Texas A&M University. The goal of AutoKeras

Keras 8.7k Jan 08, 2023
Rule Extraction Methods for Interactive eXplainability

REMIX: Rule Extraction Methods for Interactive eXplainability This repository contains a variety of tools and methods for extracting interpretable rul

Mateo Espinosa Zarlenga 21 Jan 03, 2023
Context Axial Reverse Attention Network for Small Medical Objects Segmentation

CaraNet: Context Axial Reverse Attention Network for Small Medical Objects Segmentation This repository contains the implementation of a novel attenti

401 Dec 23, 2022
ECLARE: Extreme Classification with Label Graph Correlations

ECLARE ECLARE: Extreme Classification with Label Graph Correlations @InProceedings{Mittal21b, author = "Mittal, A. and Sachdeva, N. and Agrawal

Extreme Classification 35 Nov 06, 2022
FlingBot: The Unreasonable Effectiveness of Dynamic Manipulations for Cloth Unfolding

This repository contains code for training and evaluating FlingBot in both simulation and real-world settings on a dual-UR5 robot arm setup for Ubuntu 18.04

Columbia Artificial Intelligence and Robotics Lab 70 Dec 06, 2022
clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

README clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation CVPR 2021 Authors: Suprosanna Shit and Johannes C. Paetzo

110 Dec 29, 2022
Awesome Monocular 3D detection

Awesome Monocular 3D detection Paper list of 3D detetction, keep updating! Contents Paper List 2022 2021 2020 2019 2018 2017 2016 KITTI Results Paper

Zhikang Zou 184 Jan 04, 2023
A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022)

A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022) https://arxiv.org/abs/2203.09388 Jianqi Ma, Zheto

MA Jianqi, shiki 104 Jan 05, 2023
GLIP: Grounded Language-Image Pre-training

GLIP: Grounded Language-Image Pre-training Updates 12/06/2021: GLIP paper on arxiv https://arxiv.org/abs/2112.03857. Code and Model are under internal

Microsoft 862 Jan 01, 2023
Taming Transformers for High-Resolution Image Synthesis

Taming Transformers for High-Resolution Image Synthesis CVPR 2021 (Oral) Taming Transformers for High-Resolution Image Synthesis Patrick Esser*, Robin

CompVis Heidelberg 3.5k Jan 03, 2023
Facestar dataset. High quality audio-visual recordings of human conversational speech.

Facestar Dataset Description Existing audio-visual datasets for human speech are either captured in a clean, controlled environment but contain only a

Meta Research 87 Dec 21, 2022
Implementation of Axial attention - attending to multi-dimensional data efficiently

Axial Attention Implementation of Axial attention in Pytorch. A simple but powerful technique to attend to multi-dimensional data efficiently. It has

Phil Wang 250 Dec 25, 2022
Deep Learning for 3D Point Clouds: A Survey (IEEE TPAMI, 2020)

🔥Deep Learning for 3D Point Clouds (IEEE TPAMI, 2020)

Qingyong 1.4k Jan 08, 2023
Official implementation of "Dynamic Anchor Learning for Arbitrary-Oriented Object Detection" (AAAI2021).

DAL This project hosts the official implementation for our AAAI 2021 paper: Dynamic Anchor Learning for Arbitrary-Oriented Object Detection [arxiv] [c

ming71 215 Nov 28, 2022
Gray Zone Assessment

Gray Zone Assessment Get started Clone github repository git clone https://github.com/andreanne-lemay/gray_zone_assessment.git Build docker image dock

1 Jan 08, 2022