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
A Home Assistant custom component for Lobe. Lobe is an AI tool that can classify images.

Lobe This is a Home Assistant custom component for Lobe. Lobe is an AI tool that can classify images. This component lets you easily use an exported m

Kendell R 4 Feb 28, 2022
This repository contains various models targetting multimodal representation learning, multimodal fusion for downstream tasks such as multimodal sentiment analysis.

Multimodal Deep Learning 🎆 🎆 🎆 Announcing the multimodal deep learning repository that contains implementation of various deep learning-based model

Deep Cognition and Language Research (DeCLaRe) Lab 398 Dec 30, 2022
Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling

Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling Code for the paper: Greg Ver Steeg and Aram Galstyan. "Hamiltonian Dynamics with N

Greg Ver Steeg 25 Mar 14, 2022
AI Based Smart Exam Proctoring Package

AI Based Smart Exam Proctoring Package It takes image (base64) as input: Provide Output as: Detection of Mobile phone. Detection of More than 1 person

NARENDER KESWANI 3 Sep 09, 2022
A sketch extractor for anime/illustration.

Anime2Sketch Anime2Sketch: A sketch extractor for illustration, anime art, manga By Xiaoyu Xiang Updates 2021.5.2: Upload more example results of anim

Xiaoyu Xiang 1.6k Jan 01, 2023
Code and data for ImageCoDe, a contextual vison-and-language benchmark

ImageCoDe This repository contains code and data for ImageCoDe: Image Retrieval from Contextual Descriptions. Data All collected descriptions for the

McGill NLP 27 Dec 02, 2022
A generalized framework for prototyping full-stack cooperative driving automation applications under CARLA+SUMO.

OpenCDA OpenCDA is a SIMULATION tool integrated with a prototype cooperative driving automation (CDA; see SAE J3216) pipeline as well as regular autom

UCLA Mobility Lab 726 Dec 29, 2022
Code release for "Transferable Semantic Augmentation for Domain Adaptation" (CVPR 2021)

Transferable Semantic Augmentation for Domain Adaptation Code release for "Transferable Semantic Augmentation for Domain Adaptation" (CVPR 2021) Paper

66 Dec 16, 2022
Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks

Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks This is the official code for DyReg model inroduced in Discovering Dyna

Bitdefender Machine Learning 11 Nov 08, 2022
This example implements the end-to-end MLOps process using Vertex AI platform and Smart Analytics technology capabilities

MLOps with Vertex AI This example implements the end-to-end MLOps process using Vertex AI platform and Smart Analytics technology capabilities. The ex

Google Cloud Platform 238 Dec 21, 2022
Using some basic methods to show linkages and transformations of robotic arms

roboticArmVisualizer Python GUI application to create custom linkages and adjust joint angles. In the future, I plan to add 2d inverse kinematics solv

Sandesh Banskota 1 Nov 19, 2021
A flexible framework of neural networks for deep learning

Chainer: A deep learning framework Website | Docs | Install Guide | Tutorials (ja) | Examples (Official, External) | Concepts | ChainerX Forum (en, ja

Chainer 5.8k Jan 06, 2023
PAthological QUpath Obsession - QuPath and Python conversations

PAQUO: PAthological QUpath Obsession Welcome to paquo 👋 , a library for interacting with QuPath from Python. paquo's goal is to provide a pythonic in

Bayer AG 60 Dec 31, 2022
Predicting 10 different clothing types using Xception pre-trained model.

Predicting-Clothing-Types Predicting 10 different clothing types using Xception pre-trained model from Keras library. It is reimplemented version from

AbdAssalam Ahmad 3 Dec 29, 2021
This repository is an implementation of paper : Improving the Training of Graph Neural Networks with Consistency Regularization

CRGNN Paper : Improving the Training of Graph Neural Networks with Consistency Regularization Environments Implementing environment: GeForce RTX™ 3090

THUDM 28 Dec 09, 2022
Data for "Driving the Herd: Search Engines as Content Influencers" paper

herding_data Data for "Driving the Herd: Search Engines as Content Influencers" paper Dataset description The collection contains 2250 documents, 30 i

0 Aug 17, 2021
Read and write layered TIFF ImageSourceData and ImageResources tags

Read and write layered TIFF ImageSourceData and ImageResources tags Psdtags is a Python library to read and write the Adobe Photoshop(r) specific Imag

Christoph Gohlke 4 Feb 05, 2022
NAS-Bench-x11 and the Power of Learning Curves

NAS-Bench-x11 NAS-Bench-x11 and the Power of Learning Curves Shen Yan, Colin White, Yash Savani, Frank Hutter. NeurIPS 2021. Surrogate NAS benchmarks

AutoML-Freiburg-Hannover 13 Nov 18, 2022
mmdetection version of TinyBenchmark.

introduction This project is an mmdetection version of TinyBenchmark. TODO list: add TinyPerson dataset and evaluation add crop and merge for image du

34 Aug 27, 2022
Opinionated code formatter, just like Python's black code formatter but for Beancount

beancount-black Opinionated code formatter, just like Python's black code formatter but for Beancount Try it out online here Features MIT licensed - b

Launch Platform 16 Oct 11, 2022