Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch

Related tags

Deep Learningdeep-learningtransformersartificial-intelligenceimage-to-textattention-mechanismmultimodalcontrastive-learning
Overview

CoCa - Pytorch

Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch. They were able to elegantly fit in contrastive learning to a conventional encoder / decoder (image to text) transformer, achieving SOTA 91.0% top-1 accuracy on ImageNet with a finetuned encoder.

This repository also chooses to adopt the specific transformer architecture from PaLM, for both the unimodal and multimodal transformers as well as the cross attention blocks (parallel SwiGLU feedforwards)

Yannic Kilcher presentation

Install

$ pip install coca-pytorch

Usage

First install the vit-pytorch for the image encoder, which needs to be pretrained

$ pip install vit-pytorch

Then

import torch

# import vision transformer

from vit_pytorch import ViT
from vit_pytorch.extractor import Extractor

vit = ViT(
    image_size = 256,
    patch_size = 32,
    num_classes = 1000,
    dim = 1024,
    depth = 6,
    heads = 16,
    mlp_dim = 2048
)

# do your vision transformer training

vit = Extractor(vit, return_embeddings_only = True)

# extractor will enable it so the vision transformer returns its embeddings

# import CoCa and instantiate it

from coca_pytorch.coca_pytorch import CoCa

coca = CoCa(
    dim = 512,                     # model dimension
    img_encoder = vit,             # vision transformer - image encoder, returning image embeddings as (batch, seq, dim)
    image_dim = 1024,              # image embedding dimension, if not the same as model dimensions
    num_tokens = 20000,            # number of text tokens
    unimodal_depth = 6,            # depth of the unimodal transformer
    multimodal_depth = 6,          # depth of the multimodal transformer
    dim_head = 64,                 # dimension per attention head
    heads = 8,                     # number of attention heads
    caption_loss_weight = 1.,      # weight on the autoregressive caption loss
    contrastive_loss_weight = 1.,  # weight on the contrastive loss between image and text CLS embeddings
).cuda()

# mock text and images

text = torch.randint(0, 20000, (4, 512)).cuda()
images = torch.randn(4, 3, 256, 256).cuda()

# train by giving CoCa your text and images with `return_loss = True`

loss = coca(
    text = text,
    images = images,
    return_loss = True  # set this to True to get the full caption + contrastive loss
)

loss.backward()

# do the above for as much text and images...
# then you can get the caption logits as so

logits = coca(
    text = text,
    images = images
) # (4, 512, 20000)

# and the CLIP-like text and image embeddings as

text_embeds, image_embeds = coca(
    text = text,
    images = images,
    return_embeddings = True
) # (4, 512), (4, 512)

Citations

@inproceedings{Yu2022CoCaCC,
  title   = {CoCa: Contrastive Captioners are Image-Text Foundation Models},
  author  = {Jiahui Yu and Zirui Wang and Vijay Vasudevan and Legg Yeung and Mojtaba Seyedhosseini and Yonghui Wu},
  year    = {2022}
}
@inproceedings{Chowdhery2022PaLMSL,
    title   = {PaLM: Scaling Language Modeling with Pathways},
    author  = {Aakanksha Chowdhery and Sharan Narang and Jacob Devlin and Maarten Bosma and Gaurav Mishra and Adam Roberts and Paul Barham and Hyung Won Chung and Charles Sutton and Sebastian Gehrmann and Parker Schuh and Kensen Shi and Sasha Tsvyashchenko and Joshua Maynez and Abhishek Rao and Parker Barnes and Yi Tay and Noam M. Shazeer and Vinodkumar Prabhakaran and Emily Reif and Nan Du and Benton C. Hutchinson and Reiner Pope and James Bradbury and Jacob Austin and Michael Isard and Guy Gur-Ari and Pengcheng Yin and Toju Duke and Anselm Levskaya and Sanjay Ghemawat and Sunipa Dev and Henryk Michalewski and Xavier Garc{\'i}a and Vedant Misra and Kevin Robinson and Liam Fedus and Denny Zhou and Daphne Ippolito and David Luan and Hyeontaek Lim and Barret Zoph and Alexander Spiridonov and Ryan Sepassi and David Dohan and Shivani Agrawal and Mark Omernick and Andrew M. Dai and Thanumalayan Sankaranarayana Pillai and Marie Pellat and Aitor Lewkowycz and Erica Oliveira Moreira and Rewon Child and Oleksandr Polozov and Katherine Lee and Zongwei Zhou and Xuezhi Wang and Brennan Saeta and Mark Diaz and Orhan Firat and Michele Catasta and Jason Wei and Kathleen S. Meier-Hellstern and Douglas Eck and Jeff Dean and Slav Petrov and Noah Fiedel},
    year    = {2022}
}
Comments
  • Contrastive loss should be applied to L2-normed embeddings instead of layer normed?

    Contrastive loss should be applied to L2-normed embeddings instead of layer normed?

    Hi @lucidrains, thank you for the implementation. Just wanted to confirm this with you, based on your code we're normalizing the img embedding and text embedding respectively using a learnable Layer Norm transformation before applying the contrastive loss. But based on my understanding, for contrastive loss we typically maximize the relative cosine similarity so the embeddings should be L2-normed instead of layernormed? Thank you.

    opened by fedshyvana 2
  • Extractor in vit_pytorch will detach the tensor.

    Extractor in vit_pytorch will detach the tensor.

    Thanks for your code! I think I may find a little bug. The cloned tensor in Extractor will be detached (https://github.com/lucidrains/vit-pytorch/blob/main/vit_pytorch/extractor.py#L39). So gradient may not propagate back to image encoder.

    opened by techkang 2
  • Maybe don't need this rearrange

    Maybe don't need this rearrange

    I think the logits before this line in shape (bsz, length, num_tokens) -> so I don't think here need one more rearrange https://github.com/lucidrains/CoCa-pytorch/blob/25de0b04326d8dc4c6f969e90b4466fc4894835e/coca_pytorch/coca_pytorch.py#L461

    opened by CiaoHe 2
  • How to train the model using my own dataset?

    How to train the model using my own dataset?

    Can someone tell me how to train the model using my own dataset? is it like below？But I have many images and texts...

    # train by giving CoCa your text and images with `return_loss = True`
loss = coca(
    text = text,
    images = images,
    return_loss = True  # set this to True to get the full caption + contrastive loss
)
    opened by keepcodeandsmile 1
  • why train VIT visual encoder first?

    why train VIT visual encoder first?

    Hi, thanks for sharing this repo. In the CoCA paper, both the visual encoder and text encoder are end-to end trained. But in this repo, the vit is first pretrained then fixed to train CoCa.

    opened by Flowerfan 1
  • attn_mask

    attn_mask 

    cls_mask = rearrange(text!=self.pad_id, 'b j -> b 1 j')  
attn_mask = F.pad(cls_mask, (0, 1, seq, 0), value=True)

attn_mask = rearrange(attn_mask, 'b i j -> b 1 i j')  
sim = sim.masked_fill(~attn_mask, -torch.finfo(sim.dtype).max)

    Hello, I am confused of the implement of "attn_mask". I think this padding function only can mask the last row of "sim". Could you please explain it? Perhaps it's a very fool question. Thank you so much.

    opened by pldlgb 0
  • Reproducing the results in the paper

    Reproducing the results in the paper

    Thanks for this repo. Curious, is this an independent implementation of the CoCa paper? If yes, did you reproduce any result in the paper to ensure correctness of implementation?

    opened by GKIBMNY 0
  • Generating the caption of a given image

    Generating the caption of a given image

    Hello,

    Thank you for having implemented this model. Have you already implemented some code to generate the caption of a given image? If not, do you have an idea about how you would do it in this particular architecture?

    Thank you in advance.

    opened by claudiogreco 0
Releases(0.0.7)
Owner
Phil Wang
Working with Attention. It's all we need
Phil Wang
GitHub Repository
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
Spectralformer: Rethinking hyperspectral image classification with transformers

Spectralformer: Rethinking hyperspectral image classification with transformers Danfeng Hong, Zhu Han, Jing Yao, Lianru Gao, Bing Zhang, Antonio Plaza

Danfeng Hong 102 Dec 29, 2022
PyTorch implementation of our method for adversarial attacks and defenses in hyperspectral image classification.

Self-Attention Context Network for Hyperspectral Image Classification PyTorch implementation of our method for adversarial attacks and defenses in hyp

22 Dec 02, 2022
An algorithmic trading bot that learns and adapts to new data and evolving markets using Financial Python Programming and Machine Learning.

ALgorithmic_Trading_with_ML An algorithmic trading bot that learns and adapts to new data and evolving markets using Financial Python Programming and

1 Mar 14, 2022
USAD - UnSupervised Anomaly Detection on multivariate time series

USAD - UnSupervised Anomaly Detection on multivariate time series Scripts and utility programs for implementing the USAD architecture. Implementation

116 Jan 04, 2023
Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

Pytorch Lightning 1.4k Jan 01, 2023
Repository for the AugmentedPCA Python package.

Overview This Python package provides implementations of Augmented Principal Component Analysis (AugmentedPCA) - a family of linear factor models that

Billy Carson 6 Dec 07, 2022
Official Implementation for the paper DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover’s Distance Improves Out-Of-Distribution Face Identification

DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover’s Distance Improves Out-Of-Distribution Face Identification Official Implementation for the pape

Anh M. Nguyen 36 Dec 28, 2022
Computing Shapley values using VAEAC

Shapley values and the VAEAC method In this GitHub repository, we present the implementation of the VAEAC approach from our paper "Using Shapley Value

3 Nov 23, 2022
Object Detection using YOLO from PyImageSearch

Object Detection using YOLO from PyImageSearch By applying object detection, you’ll not only be able to determine what is in an image, but also where

Mohamed NIANG 1 Feb 09, 2022
R-Drop: Regularized Dropout for Neural Networks

R-Drop: Regularized Dropout for Neural Networks R-drop is a simple yet very effective regularization method built upon dropout, by minimizing the bidi

756 Dec 27, 2022
The Dual Memory is build from a simple CNN for the deep memory and Linear Regression fro the fast Memory

Simple-DMA a simple Dual Memory Architecture for classifications. based on the paper Dual-Memory Deep Learning Architectures for Lifelong Learning of

1 Jan 27, 2022
This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

Introduction This is an official implementation of CvT: Introducing Convolutions to Vision Transformers. We present a new architecture, named Convolut

Bin Xiao 175 Jan 08, 2023
Neural Nano-Optics for High-quality Thin Lens Imaging

Neural Nano-Optics for High-quality Thin Lens Imaging Project Page | Paper | Data Ethan Tseng, Shane Colburn, James Whitehead, Luocheng Huang, Seung-H

Ethan Tseng 39 Dec 05, 2022
Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors, CVPR 2021

Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors Human POSEitioning System (H

Aymen Mir 66 Dec 21, 2022
Colab notebook and additional materials for Python-driven analysis of redlining data in Philadelphia

RedliningExploration The Google Colaboratory file contained in this repository contains work inspired by a project on educational inequality in the Ph

Benjamin Warren 1 Jan 20, 2022
Fast image augmentation library and an easy-to-use wrapper around other libraries

Albumentations Albumentations is a Python library for image augmentation. Image augmentation is used in deep learning and computer vision tasks to inc

11.4k Jan 09, 2023
This repository contains the source code of an efficient 1D probabilistic model for music time analysis proposed in ICASSP2022 venue.

Jump Reward Inference for 1D Music Rhythmic State Spaces An implementation of the probablistic jump reward inference model for music rhythmic informat

Mojtaba Heydari 25 Dec 16, 2022
SysWhispers Shellcode Loader

Shhhloader Shhhloader is a SysWhispers Shellcode Loader that is currently a Work in Progress. It takes raw shellcode as input and compiles a C++ stub

icyguider 630 Jan 03, 2023
Clairvoyance: a Unified, End-to-End AutoML Pipeline for Medical Time Series

Clairvoyance: A Pipeline Toolkit for Medical Time Series Authors: van der Schaar Lab This repository contains implementations of Clairvoyance: A Pipel

van_der_Schaar \LAB 89 Dec 07, 2022