HieCoAttenVQA issues

Wrong Answer index is -1. Error at evaluation

7

In the preprocessing script, if the answer is not in top 1000 it is removed from training example but is kept in test set and is encoded as -1. When...

ayushgithub

Error while executing train

1

Getting below error while executing **command:** `th train.lua` **Error:** `/home/ubuntu/src/torch/install/bin/luajit: /home/ubuntu/src/torch/install/share/lua/5.1/nn/THNN.lua:110: cuda runtime error (59) : device-side assert triggered at /home/ubuntu/src/torch/extra/cunn/lib/THCUNN/generic/ClassNLLCriterion.cu:87` **Entire stack trace:** `stack traceback: [C]: in function 'v'...

sandeeprepakula

Error in training

1

`torch/install/share/lua/5.1/hdf5/group.lua:312: HDF5Group:read() - no such child 'ques_train' for [HDF5Group 144115188075855879LL /]` Getting above error during training phase. Can someone help figure out what am I missing?

sandeeprepakula

Clearify using num_layers as n in LSTM implementation

Hello, I try to re-implement your paper in Keras. Now, I'm struggling with your LSTM implementation. You use num_layers as n for the LSTM initialization, but the num_layers should be...

phisad

How to process the multiple choice answer

Hi, I am confused that how to use the multiple choice answer in the multiple-choice task when training and evaluate the model? Can we process the multiple choice answer the...

WangWenshan

Torch: not enough memory: you tried to allocate 30GB.

1

$ th prepro_img_vgg.lua -input_json ../data/vqa_data_prepro.json -image_root /home/jiasenlu/data/ -cnn_proto ../image_model/VGG_ILSVRC_19_layers_deploy.prototxt -cnn_model ../image_model/VGG_ILSVRC_19_layers.caffemodel Torch: not enough memory: you tried to allocate 30GB. how to solve this memory problem ?

jijibn