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
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
Voice of Pajlada with model and weights.

Pajlada TTS Stripped down version of ForwardTacotron (https://github.com/as-ideas/ForwardTacotron) with pretrained weights for Pajlada's (https://gith

6 Sep 03, 2021
CVPR 2021 Challenge on Super-Resolution Space

Learning the Super-Resolution Space Challenge NTIRE 2021 at CVPR Learning the Super-Resolution Space challenge is held as a part of the 6th edition of

andreas 104 Oct 26, 2022
Landmarks Recogntion Web application using Streamlit.

Landmark Recognition Web-App using Streamlit Watch Tutorial for this project Source Trained model landmarks_classifier_asia_V1/1 is taken from the Ten

Kushal Bhavsar 5 Dec 12, 2022
TyXe: Pyro-based BNNs for Pytorch users

TyXe: Pyro-based BNNs for Pytorch users TyXe aims to simplify the process of turning Pytorch neural networks into Bayesian neural networks by leveragi

87 Jan 03, 2023
Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology (LMRL Workshop, NeurIPS 2021)

Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology Self-Supervised Vision Transformers Learn Visual Concepts in Histopatholog

Richard Chen 95 Dec 24, 2022
Distributed Evolutionary Algorithms in Python

DEAP DEAP is a novel evolutionary computation framework for rapid prototyping and testing of ideas. It seeks to make algorithms explicit and data stru

Distributed Evolutionary Algorithms in Python 4.9k Jan 05, 2023
The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

Swin-Unet The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"(https://arxiv.org/abs/2105.05537). A validatio

869 Jan 07, 2023
Image transformations designed for Scene Text Recognition (STR) data augmentation. Published at ICCV 2021 Workshop on Interactive Labeling and Data Augmentation for Vision.

Data Augmentation for Scene Text Recognition (ICCV 2021 Workshop) (Pronounced as "strog") Paper Arxiv Why it matters? Scene Text Recognition (STR) req

Rowel Atienza 152 Dec 28, 2022
Python binding for Khiva library.

Khiva-Python Build Documentation Build Linux and Mac OS Build Windows Code Coverage README This is the Khiva Python binding, it allows the usage of Kh

Shapelets 46 Oct 16, 2022
Testbed of AI Systems Quality Management

qunomon Description A testbed for testing and managing AI system qualities. Demo Sorry. Not deployment public server at alpha version. Requirement Ins

AIST AIRC 15 Nov 27, 2021
PlaidML is a framework for making deep learning work everywhere.

A platform for making deep learning work everywhere. Documentation | Installation Instructions | Building PlaidML | Contributing | Troubleshooting | R

PlaidML 4.5k Jan 02, 2023
Public scripts, services, and configuration for running a smart home K3S network cluster

makerhouse_network Public scripts, services, and configuration for running MakerHouse's home network. This network supports: TODO features here For mo

Scott Martin 1 Jan 15, 2022
Dogs classification with Deep Metric Learning using some popular losses

Tsinghua Dogs classification with Deep Metric Learning 1. Introduction Tsinghua Dogs dataset Tsinghua Dogs is a fine-grained classification dataset fo

QuocThangNguyen 45 Nov 09, 2022
Generating Fractals on Starknet with Cairo

StarknetFractals Generating the mandelbrot set on Starknet Current Implementation generates 1 pixel of the fractal per call(). It takes a few minutes

Orland0x 10 Jul 16, 2022
code for Grapadora research paper experimentation

Road feature embedding selection method Code for research paper experimentation Abstract Traffic forecasting models rely on data that needs to be sens

Eric López Manibardo 0 May 26, 2022
YOLTv4 builds upon YOLT and SIMRDWN, and updates these frameworks to use the most performant version of YOLO, YOLOv4

YOLTv4 builds upon YOLT and SIMRDWN, and updates these frameworks to use the most performant version of YOLO, YOLOv4. YOLTv4 is designed to detect objects in aerial or satellite imagery in arbitraril

Adam Van Etten 161 Jan 06, 2023
Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation This is the inference codes of Context-Aware Image Matting for Simultaneo

Qiqi Hou 125 Oct 22, 2022
A model which classifies reviews as positive or negative.

SentiMent Analysis In this project I built a model to classify movie reviews fromn the IMDB dataset of 50K reviews. WordtoVec : Neural networks only w

Rishabh Bali 2 Feb 09, 2022
GNNAdvisor: An Efficient Runtime System for GNN Acceleration on GPUs

GNNAdvisor: An Efficient Runtime System for GNN Acceleration on GPUs [Paper, Slides, Video Talk] at USENIX OSDI'21 @inproceedings{GNNAdvisor, title=

YUKE WANG 47 Jan 03, 2023