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
Transfer Reinforcement Learning for Differing Action Spaces via Q-Network Representations

Transfer-Learning-in-Reinforcement-Learning Transfer Reinforcement Learning for Differing Action Spaces via Q-Network Representations Final Report Tra

Trung Hieu Tran 4 Oct 17, 2022
Experiments for distributed optimization algorithms

Network-Distributed Algorithm Experiments -- This repository contains a set of optimization algorithms and objective functions, and all code needed to

Boyue Li 40 Dec 04, 2022
Lowest memory consumption and second shortest runtime in NTIRE 2022 challenge on Efficient Super-Resolution

FMEN Lowest memory consumption and second shortest runtime in NTIRE 2022 on Efficient Super-Resolution. Our paper: Fast and Memory-Efficient Network T

33 Dec 01, 2022
Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch

Implementing SYNTHESIZER: Rethinking Self-Attention in Transformer Models using Pytorch Reference Paper URL Author: Yi Tay, Dara Bahri, Donald Metzler

Myeongjun Kim 66 Nov 30, 2022
Code for our ICCV 2021 Paper "OadTR: Online Action Detection with Transformers".

Code for our ICCV 2021 Paper "OadTR: Online Action Detection with Transformers".

66 Dec 15, 2022
Conditional Generative Adversarial Networks (CGAN) for Mobility Data Fusion

This code implements the paper, Kim et al. (2021). Imputing Qualitative Attributes for Trip Chains Extracted from Smart Card Data Using a Conditional Generative Adversarial Network. Transportation Re

Eui-Jin Kim 2 Feb 03, 2022
Pytorch Implementation of Residual Vision Transformers(ResViT)

ResViT Official Pytorch Implementation of Residual Vision Transformers(ResViT) which is described in the following paper: Onat Dalmaz and Mahmut Yurt

ICON Lab 41 Dec 08, 2022
In this project, we'll be making our own screen recorder in Python using some libraries.

Screen Recorder in Python Project Description: In this project, we'll be making our own screen recorder in Python using some libraries. Requirements:

Hassan Shahzad 4 Jan 24, 2022
Airborne Optical Sectioning (AOS) is a wide synthetic-aperture imaging technique

AOS: Airborne Optical Sectioning Airborne Optical Sectioning (AOS) is a wide synthetic-aperture imaging technique that employs manned or unmanned airc

JKU Linz, Institute of Computer Graphics 39 Dec 09, 2022
A rough implementation of the paper "A Steering Algorithm for Redirected Walking Using Reinforcement Learning"

A rough implementation of the paper "A Steering Algorithm for Redirected Walking Using Reinforcement Learning"

Somnus `Chen 2 Jun 09, 2022
[内测中]前向式Python环境快捷封装工具,快速将Python打包为EXE并添加CUDA、NoAVX等支持。

QPT - Quick packaging tool 快捷封装工具 GitHub主页 | Gitee主页 QPT是一款可以“模拟”开发环境的多功能封装工具,最短只需一行命令即可将普通的Python脚本打包成EXE可执行程序,并选择性添加CUDA和NoAVX的支持,尽可能兼容更多的用户环境。 感觉还可

QPT Family 545 Dec 28, 2022
VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection (ICCV 2021)

Preparation Please see dataset/README.md to get more details about our datasets-VIL100 Please see INSTALL.md to install environment and evaluation too

82 Dec 15, 2022
[CVPR'22] COAP: Learning Compositional Occupancy of People

COAP: Compositional Articulated Occupancy of People Paper | Video | Project Page This is the official implementation of the CVPR 2022 paper COAP: Lear

Marko Mihajlovic 111 Dec 11, 2022
Pytorch implementation for RelTransformer

RelTransformer Our Architecture This is a Pytorch implementation for RelTransformer The implementation for Evaluating on VG200 can be found here Requi

Vision CAIR Research Group, KAUST 21 Nov 22, 2022
DeceFL: A Principled Decentralized Federated Learning Framework

DeceFL: A Principled Decentralized Federated Learning Framework This repository comprises codes that reproduce experiments in Ye, et al (2021), which

Huazhong Artificial Intelligence Lab (HAIL) 10 May 31, 2022
CPU inference engine that delivers unprecedented performance for sparse models

The DeepSparse Engine is a CPU runtime that delivers unprecedented performance by taking advantage of natural sparsity within neural networks to reduce compute required as well as accelerate memory b

Neural Magic 1.2k Jan 09, 2023
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

Yonglong Tian 2.2k Jan 08, 2023
Doing the asl sign language classification on static images using graph neural networks.

SignLangGNN When GNNs 💜 MediaPipe. This is a starter project where I tried to implement some traditional image classification problem i.e. the ASL si

10 Nov 09, 2022
The personal repository of the work: *DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer*.

DanceNet3D The personal repository of the work: DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer. Dataset and Results Pleas

南嘉Nanga 36 Dec 21, 2022
MOpt-AFL provided by the paper "MOPT: Optimized Mutation Scheduling for Fuzzers"

MOpt-AFL 1. Description MOpt-AFL is a AFL-based fuzzer that utilizes a customized Particle Swarm Optimization (PSO) algorithm to find the optimal sele

172 Dec 18, 2022