Skip to content

glad-gradient/visual_qa

Repository files navigation

Visual QA with Pytorch

    An implementation of paper "VQA: Visual Question Answering" with some changes.
ResNet34 is taken instead of VGGNet and the pre-trained Word2Vec model is used 
instead of training word embeddings from scratch.

Paper

VQA: Visual Question Answering

Dataset

VQA

About

Visual QA with Pytorch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published