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

Last update: Oct 04, 2022

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 "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

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)

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 Transformers (E.T.) Episodic Transformer for Vision-and-Language Navigation Alexander Pashevich, Cordelia Schmid, Chen Sun Episodic Transform

62 Dec 24, 2022

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

409 Jan 6, 2023

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

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

1 Dec 24, 2021

Transformer - Transformer in PyTorch

Transformer 完成进度 Embeddings and PositionalEncoding with example. MultiHeadAttent

1 Jan 6, 2022

Transformer Huffman coding - Complete Huffman coding through transformer

Transformer_Huffman_coding Complete Huffman coding through transformer 2022/2/19

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:

57 Nov 21, 2022

Comments

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?

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)

0.0.8(Oct 30, 2021)

Source code(tar.gz)
Source code(zip)
0.0.7(Aug 30, 2021)

Source code(tar.gz)
Source code(zip)
0.0.5(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)
0.0.4(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)
0.0.3(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)
0.0.2(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)
0.0.1(Aug 26, 2021)

Source code(tar.gz)
Source code(zip)

Owner

Phil Wang

Working with Attention. It's all we need

GitHub Repository

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

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

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

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

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

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

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

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

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

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

1 Nov 19, 2021

A flexible framework of neural networks for deep learning

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

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

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

28 Dec 09, 2022