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 10000+ hours dataset for Chinese speech recognition

WenetSpeech Official website | Paper A 10000+ Hours Multi-domain Chinese Corpus for Speech Recognition Download Please visit the official website, rea

310 Jan 03, 2023

PyAF is an Open Source Python library for Automatic Time Series Forecasting built on top of popular pydata modules.

PyAF (Python Automatic Forecasting) PyAF is an Open Source Python library for Automatic Forecasting built on top of popular data science python module

405 Jan 02, 2023

SCAAML is a deep learning framwork dedicated to side-channel attacks run on top of TensorFlow 2.x.

SCAAML (Side Channel Attacks Assisted with Machine Learning) is a deep learning framwork dedicated to side-channel attacks. It is written in python and run on top of TensorFlow 2.x.

69 Dec 21, 2022

This is the official released code for our paper, The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

The-Emergence-of-Objectness This is the official released code for our paper, The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

44 Oct 08, 2022

PyTorch implementation for the paper Pseudo Numerical Methods for Diffusion Models on Manifolds

Pseudo Numerical Methods for Diffusion Models on Manifolds (PNDM) This repo is the official PyTorch implementation for the paper Pseudo Numerical Meth

196 Jan 05, 2023

Multi-task Learning of Order-Consistent Causal Graphs (NeuRIPs 2021)

Multi-task Learning of Order-Consistent Causal Graphs (NeuRIPs 2021) Authors: Xinshi Chen, Haoran Sun, Caleb Ellington, Eric Xing, Le Song Link to pap

2 Dec 20, 2021

Nsdf: A mesh SDF with just some code we can directly paste into our raymarcher

nsdf Representing SDFs of arbitrary meshes has been a bit tricky so far. Express

5 Feb 18, 2022

A tensorflow implementation of Fully Convolutional Networks For Semantic Segmentation

##A tensorflow implementation of Fully Convolutional Networks For Semantic Segmentation. #USAGE To run the trained classifier on some images: python w

13 Nov 17, 2022

Build Low Code Automated Tensorflow, What-IF explainable models in just 3 lines of code.

Build Low Code Automated Tensorflow explainable models in just 3 lines of code.

170 Dec 26, 2022

You Only 👀 One Sequence

You Only 👀 One Sequence TL;DR: We study the transferability of the vanilla ViT pre-trained on mid-sized ImageNet-1k to the more challenging COCO obje

666 Jan 03, 2023

Codes and Data Processing Files for our paper.

Code Scripts and Processing Files for EEG Sleep Staging Paper 1. Folder Tree ./src_preprocess (data preprocessing files for SHHS and Sleep EDF) sleepE

18 Dec 12, 2022

Pytorch implementation of "Geometrically Adaptive Dictionary Attack on Face Recognition" (WACV 2022)

Geometrically Adaptive Dictionary Attack on Face Recognition This is the Pytorch code of our paper "Geometrically Adaptive Dictionary Attack on Face R

6 Nov 21, 2022

Control-Raspberry-Pi-Robot-using-Hand-Gestures - A 4WD Robot car based on Raspberry Pi that controlled by hand gestures(using openCV and mediapipe)

Control-Raspberry-Pi-Robot-using-Hand-Gestures you can see all details about thi

27 Dec 13, 2022

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering Paper: https://arxiv.org/abs/2103.00762 Running Run on the provided DTU scene cd run ba

67 Dec 28, 2022

KAPAO is an efficient multi-person human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.

KAPAO (Keypoints and Poses as Objects) KAPAO is an efficient single-stage multi-person human pose estimation model that models keypoints and poses as

664 Dec 30, 2022