Skip to content
Visual Question Reasoning on General Dependency Tree
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data/clevr pytorch_feature May 12, 2018
img vis init May 9, 2018
scripts pth0.4 Aug 19, 2018
vqa_lab pth0.4 Aug 19, 2018
.gitignore
LICENSE Create LICENSE May 11, 2018
README.md pth0.4 md Aug 19, 2018
requrements.txt prepro instruction Apr 28, 2018

README.md

Visual Question Reasoning on General Dependency Tree

Python version support PyTorch version support

This is the code for the paper on CLEVR

Visual Question Reasoning on General Dependency Tree
Qingxing Cao, Xiaodan Liang, Bailin Li, Guanbin Li, Liang Lin
Presented at CVPR 2018 (Spotlight Presentation)

If you find this code useful in your research then please cite

@InProceedings{Cao_2018_CVPR,
author = {Cao, Qingxing and Liang, Xiaodan and Li, Bailing and Li, Guanbin and Lin, Liang},
title = {Visual Question Reasoning on General Dependency Tree},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}

Requirement

  • tensorboardX
  • skimage
  • scipy
  • numpy
  • torchvision
  • h5py
  • tqdm

Data Preprocessing

Before you can train any models, you need to download the datasets; you also need to preprocess questions, and extract features for the images.

Step 1: Download the data

You can download CLEVR v1.0 (18 GB) with the common below.

$ sh data/clevr/download_dataset.sh

Step 2: Preprocess Questions

Codes for preprocessing would be available soon. For now you can download our preprocessed data with the following command:

$ sh data/clevr/download_preprocessed_questions.sh

Step 3: Extract Image Features

You can extract image features with the command below.

$ sh scripts/extract_image_feature.sh

The extracted features features_train.h5, features_val.h5, features_test.h5 woulde be placed in ./data/clevr/clevr_res101/.

Pretrained Models

You can download the pretrained models with the command below. The model will take about 2.6 GB on disk.

$ sh data/clevr/download_pretrained_model.sh

It is trained on CLEVR-train and can be validate on CLEVR-val.

Training on CLEVR

You can use the train_val.py script to train on CLEVR-train and validate the model on CLEVR-val.

$ python scripts/train_val.py --clevr_qa_dir=data/clevr/clevr_qa_dir/ --clevr_img_h5=data/clevr/clevr_res101/

The below script has the hyperparameters and settings to reproduce ACMN CLEVR results.

$ sh scripts/train_val.sh

Evaluation

You can use train_val.py to simply evaluate the model on CLEVR-val with --no_train option to skip the training process.

$ python scripts/train_val.py \
  --no_train=True \
  --clevr_qa_dir=data/clevr/clevr_qa_dir/ \
  --clevr_img_h5=data/clevr/clevr_res101/ \
  --resume=data/clevr/clevr_pretrained_model.pth

You can use test.py to generate CLEVR-test results in .json format so that you can upload to CLEVR official.

$ python scripts/test.py \
  --clevr_qa_dir=data/clevr/clevr_qa_dir/ \
  --clevr_img_h5=data/clevr/clevr_res101/ \
  --resume=data/clevr/clevr_pretrained_model.pth

Visualizing Attention Maps

You can use vis.py to visualize the attention maps discribed in Figure 4 of our paper.

$ python scripts/vis.py \
  --clevr_qa_dir=data/clevr/clevr_qa_dir/ \
  --clevr_img_h5=data/clevr/clevr_res101/ \
  --clevr_img_png=data/clevr/CLEVR_v1.0/ \
  --clevr_load_png=True \
  --logdir=logs/attmaps \
  --resume=data/clevr/clevr_pretrained_model.pth
You can’t perform that action at this time.