easy-vqa
The official repository for the Easy Visual Question Answering (easy-VQA) dataset. Contains:
- the official Python package for the dataset
- the source code for generating the dataset
Read the easy-VQA blog post 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 of a model trained on the dataset.
Example Images
(these image links above only work on Github)
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:
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.
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.
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
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:
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.
Metadata
Release files for easy-vqa 1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| easy-vqa-1.0.tar.gz | 2.0 MB | Without provenance | Details for easy-vqa-1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| easy_vqa-1.0-py3-none-any.whl | Python 3 | none | any | Details for easy_vqa-1.0-py3-none-any.whl |
Total release size: 5.2 MB
Release files / easy-vqa-1.0.tar.gz
| Download URL | easy-vqa-1.0.tar.gz |
|---|---|
| Size | 2.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f49e98f314ef1ed1606f1b9d8ec33200bc9b6f6e45a0a6503b1c171a087daaee
|
|
BLAKE2b-256 checksum How to use checksums |
5147b26fe69575594d45801cb368a43da7d0a720165177dd12caef69e5446e12
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/40.6.2 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.7.2
|
Release files / easy_vqa-1.0-py3-none-any.whl
| Download URL | easy_vqa-1.0-py3-none-any.whl |
|---|---|
| Size | 3.2 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fcb51b309b78c7b00f97b64cdbcbcf5c105f94da1b39c0796cee5a787c4f650f
|
|
BLAKE2b-256 checksum How to use checksums |
32e7dbdd733ea110ff04c8b0b7ce7d49acce06f1dd18ed304d9f8f9b3f26c1a3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/40.6.2 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.7.2
|
Security for easy-vqa 1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.