Compact Bidirectional Transformer for Image Captioning

Related tags

Deep LearningCBTrans
Overview

Compact Bidirectional Transformer for Image Captioning

Requirements

  • Python 3.8
  • Pytorch 1.6
  • lmdb
  • h5py
  • tensorboardX

Prepare Data

  1. Please use git clone --recurse-submodules to clone this repository and remember to follow initialization steps in coco-caption/README.md.
  2. Download the preprocessd dataset from this link and extract it to data/.
  3. Please download the converted VinVL feature from this link and place them under data/mscoco_VinVL/. You can also optionally follow this instruction to prepare the fixed or adaptive bottom-up features extracted by Anderson and place them under data/mscoco/ or data/mscoco_adaptive/.
  4. Download part checkpoints from here and extract them to save/.

Offline Evaluation

To reproduce the results of single CBTIC model on Karpathy test split, just run

python  eval.py  --model  save/nsc-transformer-cb-VinVL-feat/model-best.pth   --infos_path  save/nsc-transformer-cb-VinVL-feat/infos_nsc-transformer-cb-VinVL-feat-best.pkl      --beam_size   2   --id  nsc-transformer-cb-VinVL-feat   --split test

To reproduce the results of ensemble of CBTIC models on Karpathy test split, just run

python eval_ensemble.py   --ids   nsc-transformer-cb-VinVL-feat  nsc-transformer-cb-VinVL-feat-seed1   nsc-transformer-cb-VinVL-feat-seed2  nsc-transformer-cb-VinVL-feat-seed3 --weights  1 1 1 1  --beam_size  2   --split  test

Online Evaluation

Please first run

python eval_ensemble.py   --split  test  --language_eval 0  --ids   nsc-transformer-cb-VinVL-feat  nsc-transformer-cb-VinVL-feat-seed1   nsc-transformer-cb-VinVL-feat-seed2  nsc-transformer-cb-VinVL-feat-seed3 --weights  1 1 1 1  --input_json  data/cocotest.json  --input_fc_dir data/mscoco_VinVL/cocobu_test2014/cocobu_fc --input_att_dir  data/mscoco_VinVL/cocobu_test2014/cocobu_att   --input_label_h5    data/cocotalk_bw_label.h5    --language_eval 0        --batch_size  128   --beam_size   2   --id   captions_test2014_cbtic_results

and then follow the instruction to upload results.

Training

  1. In the first training stage, such as using VinVL feature, run
python  train.py   --noamopt --noamopt_warmup 20000   --seq_per_img 5 --batch_size 10 --beam_size 1 --learning_rate 5e-4 --num_layers 6 --input_encoding_size 512 --rnn_size 2048 --learning_rate_decay_start 0  --scheduled_sampling_start 0  --save_checkpoint_every 3000 --language_eval 1 --val_images_use 5000 --max_epochs 15     --checkpoint_path   save/transformer-cb-VinVL-feat   --id   transformer-cb-VinVL-feat   --caption_model  cbt     --input_fc_dir   data/mscoco_VinVL/cocobu_fc   --input_att_dir   data/mscoco_VinVL/cocobu_att    --input_box_dir    data/mscoco_VinVL/cocobu_box
  1. Then in the second training stage, you need two GPUs with 12G memory each, please copy the above pretrained model first
cd save
./copy_model.sh  transformer-cb-VinVL-feat    nsc-transformer-cb-VinVL-feat
cd ..

and then run

python  train.py    --seq_per_img 5 --batch_size 10 --beam_size 1 --learning_rate 1e-5 --num_layers 6 --input_encoding_size 512 --rnn_size 2048  --save_checkpoint_every 3000 --language_eval 1 --val_images_use 5000 --self_critical_after 14  --max_epochs    30  --start_from   save/nsc-transformer-cb-VinVL-feat     --checkpoint_path   save/nsc-transformer-cb-VinVL-feat   --id  nsc-transformer-cb-VinVL-feat   --caption_model  cbt    --input_fc_dir   data/mscoco_VinVL/cocobu_fc   --input_att_dir   data/mscoco_VinVL/cocobu_att    --input_box_dir    data/mscoco_VinVL/cocobu_box

Note

  1. Even if fixing all random seed, we find that the results of the two runs are still slightly different when using DataParallel on two GPUs. However, the results can be reproduced exactly when using one GPU.
  2. If you are interested in the ablation studies, you can use the git reflog to list all commits and use git reset --hard commit_id to change to corresponding commit.

Citation

@misc{zhou2022compact,
      title={Compact Bidirectional Transformer for Image Captioning}, 
      author={Yuanen Zhou and Zhenzhen Hu and Daqing Liu and Huixia Ben and Meng Wang},
      year={2022},
      eprint={2201.01984},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Acknowledgements

This repository is built upon self-critical.pytorch. Thanks for the released code.

Owner
YE Zhou
YE Zhou
GitHub Repository
Python implementation of Bayesian optimization over permutation spaces.

Bayesian Optimization over Permutation Spaces This repository contains the source code and the resources related to the paper "Bayesian Optimization o

Aryan Deshwal 9 Dec 23, 2022
Implementation of "Semi-supervised Domain Adaptive Structure Learning"

Semi-supervised Domain Adaptive Structure Learning - ASDA This repo contains the source code and dataset for our ASDA paper. Illustration of the propo

3 Dec 13, 2021
UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset

TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation By Vladimir Iglovikov and Alexey Shvets Introduction TernausNet is

Vladimir Iglovikov 1k Dec 28, 2022
Progressive Growing of GANs for Improved Quality, Stability, and Variation

Progressive Growing of GANs for Improved Quality, Stability, and Variation — Official TensorFlow implementation of the ICLR 2018 paper Tero Karras (NV

Tero Karras 5.9k Jan 05, 2023
A tensorflow/keras implementation of StyleGAN to generate images of new Pokemon.

PokeGAN A tensorflow/keras implementation of StyleGAN to generate images of new Pokemon. Dataset The model has been trained on dataset that includes 8

19 Jul 26, 2022
Voxel-based Network for Shape Completion by Leveraging Edge Generation (ICCV 2021, oral)

Voxel-based Network for Shape Completion by Leveraging Edge Generation This is the PyTorch implementation for the paper "Voxel-based Network for Shape

10 Dec 04, 2022
上海交通大学全自动抢课脚本，支持准点开抢与抢课后持续捡漏两种模式。2021/06/08更新。

Welcome to Course-Bullying-in-SJTU-v3.1！ 2021/6/8 紧急更新v3.1 更新说明 为了更好地保护用户隐私，将原来用户名+密码的登录方式改为微信扫二维码+cookie登录方式，不再需要配置使用pytesseract。在使用扫码登录模式时，请稍等，二维码将马

87 Sep 13, 2022
RLDS stands for Reinforcement Learning Datasets

RLDS RLDS stands for Reinforcement Learning Datasets and it is an ecosystem of tools to store, retrieve and manipulate episodic data in the context of

Google Research 135 Jan 01, 2023
An Exact Solver for Semi-supervised Minimum Sum-of-Squares Clustering

PC-SOS-SDP: an Exact Solver for Semi-supervised Minimum Sum-of-Squares Clustering PC-SOS-SDP is an exact algorithm based on the branch-and-bound techn

Antonio M. Sudoso 1 Nov 13, 2022
PyTorch implementation of hand mesh reconstruction described in CMR and MobRecon.

Hand Mesh Reconstruction Introduction This repo is the PyTorch implementation of hand mesh reconstruction described in CMR and MobRecon. Update 2021-1

Xingyu Chen 236 Dec 29, 2022
《DeepViT: Towards Deeper Vision Transformer》(2021)

DeepViT This repo is the official implementation of "DeepViT: Towards Deeper Vision Transformer". The repo is based on the timm library (https://githu

109 Dec 02, 2022
Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

[Paper] [Project page] This repository contains code for the paper: Andrew Owens, Alexei A. Efros. Audio-Visual Scene Analysis with Self-Supervised Mu

Andrew Owens 202 Dec 13, 2022
This project provides the code and datasets for 'CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection', CVPR 2019.

Code-and-Dataset-for-CapSal This project provides the code and datasets for 'CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detec

lu zhang 48 Aug 19, 2022
ADOP: Approximate Differentiable One-Pixel Point Rendering

ADOP: Approximate Differentiable One-Pixel Point Rendering Abstract: We present a novel point-based, differentiable neural rendering pipeline for scen

Darius Rückert 1.9k Jan 06, 2023
PyImpetus is a Markov Blanket based feature subset selection algorithm that considers features both separately and together as a group in order to provide not just the best set of features but also the best combination of features

PyImpetus PyImpetus is a Markov Blanket based feature selection algorithm that selects a subset of features by considering their performance both indi

Atif Hassan 103 Dec 14, 2022
3D detection and tracking viewer (visualization) for kitti & waymo dataset

3D detection and tracking viewer (visualization) for kitti & waymo dataset

222 Jan 08, 2023
PyTorch code for: Learning to Generate Grounded Visual Captions without Localization Supervision

Learning to Generate Grounded Visual Captions without Localization Supervision This is the PyTorch implementation of our paper: Learning to Generate G

Chih-Yao Ma 41 Nov 17, 2022
Virtual Dance Reality Stage: a feature that offers you to share a stage with another user virtually

Portrait Segmentation using Tensorflow This script removes the background from an input image. You can read more about segmentation here Setup The scr

291 Dec 24, 2022
AntiFuzz: Impeding Fuzzing Audits of Binary Executables

AntiFuzz: Impeding Fuzzing Audits of Binary Executables Get the paper here: https://www.usenix.org/system/files/sec19-guler.pdf Usage: The python scri

Chair for Sys­tems Se­cu­ri­ty 88 Dec 21, 2022
Fast and simple implementation of RL algorithms, designed to run fully on GPU.

RSL RL Fast and simple implementation of RL algorithms, designed to run fully on GPU. This code is an evolution of rl-pytorch provided with NVIDIA's I

Robotic Systems Lab - Legged Robotics at ETH Zürich 68 Dec 29, 2022