Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
:grey_question: Visual Question Answering in Torch
| Date | Stars |
|---|---|
| 2026-07-24 | 486 |
| 2026-07-25 | 486 |
| 2026-07-28 | 486 |
| 2026-07-30 | 486 |
| 2026-08-06 | 486 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# neural-vqa [](https://gitter.im/abhshkdz/neural-vqa?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge) This is an experimental Torch implementation of the VIS + LSTM visual question answering model from the paper [Exploring Models and Data for Image Question Answering][2] by Mengye Ren, Ryan Kiros & Richard Zemel.  ## Setup Requirements: - [Torch][10] - [loadcaffe][9] Download the [MSCOCO][11] train+val images and [VQA][1] data using `sh data/download_data.sh`. Extract all the downloaded zip files inside the `data` folder. ``` unzip Annotations_Train_mscoco.zip unzip Questions_Train_mscoco.zip unzip train2014.zip unzip Annotations_Val_mscoco.zip unzip Questions_Val_mscoco.zip unzip val2014.zip ``` If you had them downloaded already, copy over the `train2014` and `val2014` image folders and VQA JSON files to the `data` folder. Download the [VGG-19][7] Caffe model and prototxt using `sh models/download_models.sh`. ### Known issues - To avoid memory issues with LuaJIT, install Torch with Lua 5.1 (`TORCH_LUA_VERSION=LUA51 ./install.sh`). More instructions [here][4]. - If working with plain Lua, [luaffifb][8] may be needed for [loadcaffe][9], unless using pre-extracted fc7 features. ## Usage ### Extract image features ``` th extract_fc7.lua -split train th extract_fc7.lua -split val ``` #### Options - `batch_size`: Batch size. Default is 10. - `split`: train/val. Default is `train`. - `gpuid`: 0-indexed id of GPU to use. Default is -1 = CPU. - `proto_file`: Path to the `deploy.prototxt` file for the VGG Caffe model. Default is `models/VGG_ILSVRC_19_layers_deploy.prototxt`. - `model_file`: Path to the `.caffemodel` file for the VGG Caffe model. Default is `models/VGG_ILSVRC_19_layers.caffemodel`. - `data_dir`: Data directory. Default is `data`. - `feat_layer`: Layer to extract features from. Default is `fc7`. - `input_image_dir`: Image directory. Default is `data`. ### Training ``` th train.lua ``` #### Options - `rnn_size`: Size of LSTM internal state. Default is 512. - `num_layers`: Number of layers in LSTM - `embedding_size`: Size of word embeddings. Default is 512. - `learning_rate`: Learning rate. Default is 4e-4. - `learning_rate_decay`: Learning rate decay factor. Default is 0.95. - `learning_rate_decay_after`: In number of epochs, when to start decaying the learning rate. Default is 15. - `alpha`: Alpha for adam. Default is 0.8 - `beta`: Beta used for adam. Default is 0.999. - `epsilon`: Denominator term for smoothing. Default is 1e-8. - `batch_size`: Batch size. Default is 64. - `max_epochs`: Number of full passes through the training data. Default is 15. - `dropout`: Dropout for regularization. Probability of dropping input. Default is 0.5. - `init_from`: Initialize network parameters from checkpoint at this path. - `save_every`: No. of iterations after which to checkpoint. Default is 1000. - `train_fc7_file`: Path to fc7 features of training set. Default is `data/train_fc7.t7`. - `fc7_image_id_file`: Path to fc7 image ids of training set. Default is `data/train_fc7_image_id.t7`. - `val_fc7_file`: Path to fc7 features of validation set. Default is `data/val_fc7.t7`. - `val_fc7_image_id_file`: Path to fc7 image ids of validation set. Default is `data/val_fc7_image_id.t7`. - `data_dir`: Data directory. Default is `data`. - `checkpoint_dir`: Checkpoint directory. Default is `checkpoints`. - `savefile`: Filename to save checkpoint to. Default is `vqa`. - `gpuid`: 0-indexed id of GPU to use. Default is -1 = CPU. ### Testing ``` th predict.lua -checkpoint_file checkpoints/vqa_epoch23.26_0.4610.t7 -input_image_path data/train2014/COCO_train2014_000000405541.jpg -question 'What is the cat on?' ``` #### Options - `checkpoint_file`: Path to model checkpoint to initialize network parameters from - `input_image_path`: Path t
Excerpt of 6,582 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:58acaf141dffdf3a, topic:deep-learning
matched fp:58acaf141dffdf3a, topic:computer-vision
matched fp:58acaf141dffdf3a, topic:natural-language-processing