# GT-Vision-Lab/VQA\_LSTM\_CNN

<https://repo.masters-masters.com/en/repos/GT-Vision-Lab/VQA_LSTM_CNN>

[Home](https://repo.masters-masters.com/en) › [GT-Vision-Lab](https://repo.masters-masters.com/en/owners/GT-Vision-Lab) › [VQA\_LSTM\_CNN](https://repo.masters-masters.com/en/repos/GT-Vision-Lab/VQA_LSTM_CNN)

GT-Vision-Lab/VQA\_LSTM\_CNN has 386 stars on GitHub. Its RepoMasters card: Alpha tier. Train a deeper LSTM and normalized CNN Visual Question Answering model…

| Field | Value |
| --- | --- |
| Owner | [GT-Vision-Lab](https://repo.masters-masters.com/en/owners/GT-Vision-Lab) |
| Stars | 386 |
| Forks | 131 |
| Language | [Lua](https://repo.masters-masters.com/en/languages/lua) |
| License | None |
| Created | 2015 |
| Tier | [Alpha (250 to 699 ★)](https://repo.masters-masters.com/en/ranks/b_movie) |
| View on GitHub | [GT-Vision-Lab/VQA\_LSTM\_CNN](https://github.com/GT-Vision-Lab/VQA_LSTM_CNN) |

## Repository

Train a deeper LSTM and normalized CNN Visual Question Answering model. This current code can get 58.16 on OpenEnded and 63.09 on Multiple-Choice on test-standard.

The tier for repos with 250 to 699 ★. Published odds per card pulled: 20%. Rarity: Uncommon.

## More repos by GT-Vision-Lab

- [GT-Vision-Lab/VQA · ★ 395 · Python · Alpha](https://repo.masters-masters.com/en/repos/GT-Vision-Lab/VQA)

## Nearby in Lua

- [femga/rdr3\_discoveries · ★ 387 · Lua · Alpha](https://repo.masters-masters.com/en/repos/femga/rdr3_discoveries)
- [Mogli12/VehicleControlAddon · ★ 386 · Lua · Alpha](https://repo.masters-masters.com/en/repos/Mogli12/VehicleControlAddon)
- [jesseleite/noirbuddy.nvim · ★ 386 · Lua · Alpha](https://repo.masters-masters.com/en/repos/jesseleite/noirbuddy.nvim)
- [JoshParnell/ltheory · ★ 385 · Lua · Alpha](https://repo.masters-masters.com/en/repos/JoshParnell/ltheory)
- [MaximilianLloyd/ascii.nvim · ★ 385 · Lua · Alpha](https://repo.masters-masters.com/en/repos/MaximilianLloyd/ascii.nvim)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.