Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/vzhou842/easy-vqa
The Easy Visual Question Answering dataset.
https://github.com/vzhou842/easy-vqa
dataset easy-vqa visual-question-answering vqa vqa-dataset
Last synced: 14 days ago
JSON representation
The Easy Visual Question Answering dataset.
- Host: GitHub
- URL: https://github.com/vzhou842/easy-vqa
- Owner: vzhou842
- License: mit
- Created: 2019-10-26T22:39:10.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2023-10-03T21:39:31.000Z (about 1 year ago)
- Last Synced: 2024-04-23T20:50:11.610Z (7 months ago)
- Topics: dataset, easy-vqa, visual-question-answering, vqa, vqa-dataset
- Language: Python
- Homepage: https://pypi.org/project/easy-vqa/
- Size: 9.5 MB
- Stars: 32
- Watchers: 3
- Forks: 11
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# easy-vqa
[](https://travis-ci.com/vzhou842/easy-vqa)
The official repository for the Easy Visual Question Answering (easy-VQA) dataset. Contains:
- the official [Python package](https://pypi.org/project/easy-vqa/) for the dataset
- the source code for generating the dataset
Read [the easy-VQA blog post](https://victorzhou.com/blog/easy-vqa/) for more.
## About the Dataset
easy-VQA contains
- 4,000 train images and 38,575 train questions.
- 1,000 test images and 9,673 test questions.
- 13 total possible answers.
- 28,407 training questions that are yes/no.
- 7,136 testing questions that are yes/no.
All images are 64x64 color images. See a [live demo](https://easy-vqa-demo.victorzhou.com/) of a model trained on the dataset.
### Example Images
_(these image links above only work on [Github](https://github.com/vzhou842/easy-VQA))_
### Example Questions
- _What color is the rectangle?_
- _Does the image contain a triangle?_
- _Is no blue shape present?_
- _What shape does the image contain?_
## Installing the Package
`pip install easy-vqa`
## Using the Package
### Questions
Each question has 3 parts:
- the **question text**
- the **answer**
- the **image ID**
The question getters return corresponding **arrays** for each of the 3 parts:
```python
from easy_vqa import get_train_questions, get_test_questions
train_questions, train_answers, train_image_ids = get_train_questions()
test_questions, test_answers, test_image_ids = get_test_questions()
# Question 0 is at index 0 for all 3 arrays:
print(train_questions[0]) # what shape does the image contain?
print(train_answers[0]) # circle
print(train_image_ids[0]) # 0
```
### Images
The image path getters return dicts that map **image ID** to **absolute paths** that can be used to load the image.
```python
from easy_vqa import get_train_image_paths, get_test_image_paths
train_image_paths = get_train_image_paths()
test_image_paths = get_test_image_paths()
print(train_image_paths[0]) # ends in easy_vqa/data/train/images/0.png
```
### Answers
The answers getter returns an **array** of all possible answers.
```python
from easy_vqa import get_answers
answers = get_answers()
print(answers) # ['teal', 'brown', 'black', 'gray', 'yes', 'blue', 'rectangle', 'yellow', 'triangle', 'red', 'circle', 'no', 'green']
```
## Generating the Dataset
The easy-VQA dataset was generated by running
```shell
python gen_data/generate_data.py
```
which writes to the `easy_vqa/data/` directory. Be sure to install the dependencies for dataset generation running `generate_data.py`:
```shell
pip install -r gen_data/requirements.txt
```
If you want to generate a larger easy-VQA dataset, simply modify the `NUM_TRAIN` and `NUM_TEST` constants in `generate_data.py`. Otherwise, if you want to modify the dataset itself, the files and code in the `gen_data/` directory should be pretty self-explanatory.