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
Various operations like path tracking, counting, etc by using yolov5

Object-tracing-with-YOLOv5 Various operations like path tracking, counting, etc by using yolov5

Pawan Valluri 5 Nov 28, 2022
GPU implementation of $k$-Nearest Neighbors and Shared-Nearest Neighbors

GPU implementation of kNN and SNN GPU implementation of $k$-Nearest Neighbors and Shared-Nearest Neighbors Supported by numba cuda and faiss library E

Hyeon Jeon 7 Nov 23, 2022
Like Dirt-Samples, but cleaned up

Clean-Samples Like Dirt-Samples, but cleaned up, with clear provenance and license info (generally a permissive creative commons licence but check the

TidalCycles 39 Nov 30, 2022
In generative deep geometry learning, we often get many obj files remain to be rendered

a python prompt cli script for blender batch render In deep generative geometry learning, we always get many .obj files to be rendered. Our rendered i

Tian-yi Liang 1 Mar 20, 2022
A real-time speech emotion recognition application using Scikit-learn and gradio

Speech-Emotion-Recognition-App A real-time speech emotion recognition application using Scikit-learn and gradio. Requirements librosa==0.6.3 numpy sou

Son Tran 6 Oct 04, 2022
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

Tensorpack is a neural network training interface based on TensorFlow. Features: It's Yet Another TF high-level API, with speed, and flexibility built

Tensorpack 6.2k Jan 09, 2023
Collection of Docker images for ML/DL and video processing projects

Collection of Docker images for ML/DL and video processing projects. Overview of images Three types of images differ by tag postfix: base: Python with

OSAI 87 Nov 22, 2022
Implementations of LSTM: A Search Space Odyssey variants and their training results on the PTB dataset.

An LSTM Odyssey Code for training variants of "LSTM: A Search Space Odyssey" on Fomoro. Check out the blog post. Training Install TensorFlow. Clone th

Fomoro AI 95 Apr 13, 2022
Learning Tracking Representations via Dual-Branch Fully Transformer Networks

Learning Tracking Representations via Dual-Branch Fully Transformer Networks DualTFR ⭐ We achieves the runner-ups for both VOT2021ST (short-term) and

phiphi 19 May 04, 2022
shufflev2-yolov5:lighter, faster and easier to deploy

shufflev2-yolov5: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size

pogg 1.5k Jan 05, 2023
Python with OpenCV - MediaPip Framework Hand Detection

Python HandDetection Python with OpenCV - MediaPip Framework Hand Detection Explore the docs » Contact Me About The Project It is a Computer vision pa

2 Jan 07, 2022
Learning to Self-Train for Semi-Supervised Few-Shot

Learning to Self-Train for Semi-Supervised Few-Shot Classification This repository contains the TensorFlow implementation for NeurIPS 2019 Paper "Lear

86 Dec 29, 2022
The Official Repository for "Generalized OOD Detection: A Survey"

Generalized Out-of-Distribution Detection: A Survey 1. Overview This repository is with our survey paper: Title: Generalized Out-of-Distribution Detec

Jingkang Yang 338 Jan 03, 2023
Offical code for the paper: "Growing 3D Artefacts and Functional Machines with Neural Cellular Automata" https://arxiv.org/abs/2103.08737

Growing 3D Artefacts and Functional Machines with Neural Cellular Automata Video of more results: https://www.youtube.com/watch?v=-EzztzKoPeo Requirem

Robotics Evolution and Art Lab 51 Jan 01, 2023
Gesture Volume Control v.2

Gesture volume control v.2 In this project I am going to learn how to use Gesture Control to change the volume of a computer. I first look into hand t

Pavel Dat 23 Dec 26, 2022
Sky Computing: Accelerating Geo-distributed Computing in Federated Learning

Sky Computing Introduction Sky Computing is a load-balanced framework for federated learning model parallelism. It adaptively allocate model layers to

HPC-AI Tech 72 Dec 27, 2022
Another pytorch implementation of FCN (Fully Convolutional Networks)

FCN-pytorch-easiest Trying to be the easiest FCN pytorch implementation and just in a get and use fashion Here I use a handbag semantic segmentation f

Y. Dong 158 Dec 21, 2022
CaFM-pytorch ICCV ACCEPT Introduction of dataset VSD4K

CaFM-pytorch ICCV ACCEPT Introduction of dataset VSD4K Our dataset VSD4K includes 6 popular categories: game, sport, dance, vlog, interview and city.

96 Jul 05, 2022
A list of all named GANs!

The GAN Zoo Every week, new GAN papers are coming out and it's hard to keep track of them all, not to mention the incredibly creative ways in which re

Avinash Hindupur 12.9k Jan 08, 2023