abhshkdz / neural-vqa Goto Github PK

:grey_question: Visual Question Answering in Torch

Home Page: https://arxiv.org/abs/1505.02074

Shell 0.89% Lua 99.11%

torch deep-learning computer-vision natural-language-processing

neural-vqa's Introduction

neural-vqa

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 by Mengye Ren, Ryan Kiros & Richard Zemel.

Setup

Requirements:

Download the MSCOCO train+val images and VQA 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 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.
If working with plain Lua, luaffifb may be needed for loadcaffe, 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 to input image
question: Question string

Sample predictions

Randomly sampled image-question pairs from the VQA test set, and answers predicted by the VIS+LSTM model.

Q: What animals are those? A: Sheep

Q: What color is the frisbee that's upside down? A: Red

Q: What is flying in the sky? A: Kite

Q: What color is court? A: Blue

Q: What is in the standing person's hands? A: Bat

Q: Are they riding horses both the same color? A: No

Q: What shape is the plate? A: Round

Q: Is the man wearing socks? A: Yes

Q: What is over the woman's left shoulder? A: Fork

Q: Where are the pink flowers? A: On wall

Implementation Details

Last hidden layer image features from VGG-19
Zero-padded question sequences for batched implementation
Training questions are filtered for top_n answers, top_n = 1000 by default (~87% coverage)

Pretrained model and data files

To reproduce results shown on this page or try your own image-question pairs, download the following and run predict.lua with the appropriate paths.

vqa_epoch23.26_0.4610.t7 (Serialized using Lua51) [GPU] [CPU]
answers_vocab.t7
questions_vocab.t7
data.t7

References

Exploring Models and Data for Image Question Answering, Ren et al., NIPS15
VQA: Visual Question Answering, Antol et al., ICCV15

License

MIT

neural-vqa's People

Contributors

Stargazers

Watchers

Forkers

jakezhaojb benjamesbabala ml-lab kratarth1203 codeaudit caomw lngvietthang zencoding phecy kevinwenya nikhilagrima hamedmp wavelets yanweifu jslhs andradeandrey apextw xuanhan863 scatterbrain333 fdoperezi ml639 jguilhermemv soroushmehr robertogemartin copyfun eriche2016 vseledkin kundan2510 tommy-kwon redzgn gitter-badger wgapl tigerneil hitluobin pjpan xsongx chagge tybxiaobao khushigupta zjucsxxd liu09114 chemccandless ritali sqxiang realentertain yadavankit dylan-fan cloudreamer cc13ny morusu deshraj manli009 stevenlol arasharchor lijian8 vyraun suraj-deshmukh walkoncross tianfeng80 rajats920 tonychouzju daidengxin suhmily sp2014 aekanshkansal1 o-github-o stalin18 lemonnight charlottebronte jijibn iqbal-chowdhury shubhampachori12110095 amshb001 mohanarunachalam badripatro jryongithub yyf17 afcarl lankagege changquanyou meelement davidzeng2018 msj905 yavuzkomecoglu coolyr wodejing soar200 jocelyn1981 sakastlord strategist922

neural-vqa's Issues

2vis-lstm

Hello,
how can I change this part of code to forward the image fisrt
also could u plz provide 2vis-lstm code ?
for t = 1, loader.q_max_length do
lst = lstm_clones[t]:forward{qf:select(2,t), unpack(rnn_state[t-1])}
-- at every time step, set the rnn state (h_t, c_t) to be passed as input in next time step
rnn_state[t] = {}
for i = 1, #init_state do table.insert(rnn_state[t], lst[i]) end
end

-- after completing the unrolled LSTM forward pass with question features, forward the image features
lst = lstm_clones[loader.q_max_length + 1]:forward{imf, unpack(rnn_state[loader.q_max_length])}

Error ---- predict.lua -checkpoint_file vqa_epoch15.00_0.4576.t7 -input_image_path data/train2014/COCO_train2014_000000405541.jpg -question 'What is the cat on?'

DaviddeMacBook-Pro:neural-vqa-master lihong$ th predict.lua -checkpoint_file vqa_epoch15.00_0.4576.t7 -input_image_path data/train2014/COCO_train2014_000000405541.jpg -question 'What is the cat on?'
/Users/lihong/torch/install/bin/luajit: ./utils/DataLoader.lua:35: attempt to index local 'train_questions_attr' (a nil value)
stack traceback:
./utils/DataLoader.lua:35: in function 'create'
predict.lua:59: in main chunk
[C]: in function 'dofile'
...hong/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
[C]: at 0x010ad1fbd0

not enough memory

envy@ub1404:/os_pri/github/neural-vqa$ th extract_fc7.lua -split train
questions_vocab.t7, answers_vocab.t7 or data.t7 files do not exist. Running preprocessing...
one-time setup: preprocessing...
creating vocabulary mapping...
/home/envy/torch/install/bin/luajit: not enough memory
envy@ub1404:/os_pri/github/neural-vqa$
envy@ub1404:/os_pri/github/neural-vqa$
envy@ub1404:/os_pri/github/neural-vqa$ th extract_fc7.lua -split val
questions_vocab.t7, answers_vocab.t7 or data.t7 files do not exist. Running preprocessing...
one-time setup: preprocessing...
creating vocabulary mapping...
/home/envy/torch/install/bin/luajit: not enough memory
envy@ub1404:~/os_pri/github/neural-vqa$

My Machine:
i7 6700HQ
16GB
GTX 950M

Performance and memory issue with training

I am running this command "th extract_fc7.lua -split train" is taking very long time about 4days, and also I have 16gb ram and it is growing the size fairly quickly and is getting to out of memory within 1day.

I have a i5, 16gb RAM machine, can I run the training completely? if not what kind of machine I need.

Please help.

unknown Torch class <torch.CudaTensor>

while extracting the image features using th extract_fc7.lua -split train
bad argument 3 to 'narrow' out of range at (path_to_torch/pkg/torch/lib/TH/generic/THTensor.c:351)
above error is thrown

should this directory works well?

rzai@rzai00:~/prj/neural-vqa$ tree
.
├── data
│   ├── download_data.sh
│   ├── mscoco_train2014_annotations.json
│   ├── mscoco_val2014_annotations.json
│   ├── MultipleChoice_mscoco_train2014_questions.json
│   ├── MultipleChoice_mscoco_val2014_questions.json
│   ├── OpenEnded_mscoco_train2014_questions.json
│   ├── OpenEnded_mscoco_val2014_questions.json
│   ├── train2014
│   └── val2014
├── evaluate.lua
├── extract_fc7.lua
├── lstm.lua
├── models
│   ├── download_models.sh
│   ├── VGG_ILSVRC_19_layers.caffemodel -> /media/rzai/ai_data/VGG_ILSVRC_19_layers.caffemodel
│   └── VGG_ILSVRC_19_layers_deploy.prototxt
├── predict.lua
├── README.md
├── train.lua
└── utils
├── DataLoader.lua
├── JSON.lua
└── misc.lua

3 directories, 21 files
rzai@rzai00:~/prj/neural-vqa$

Error while evaluating through pretrained checkpoint

I am trying to get the results through pretrained cpu checkpoint. My command is

th predict.lua -checkpoint_file checkpoints/vqa_epoch23.26_0.4610_cpu.t7 -input_image_path data/train2014/COCO_train2014_000000405541.jpg -question 'What is the cat on?' -gpuid -1

Error given is
Loading data files...
/home/aekansh/torch/install/bin/lua: ...e/aekansh/torch/install/share/lua/5.1/torch/File.lua:259: read error: read 0 blocks instead of 1 at /home/aekansh/torch/pkg/torch/lib/TH/THDiskFile.c:349
stack traceback:
[C]: in function 'readInt'
...e/aekansh/torch/install/share/lua/5.1/torch/File.lua:259: in function 'readObject'
...e/aekansh/torch/install/share/lua/5.1/torch/File.lua:368: in function 'readObject'
...e/aekansh/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
...e/aekansh/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
...e/aekansh/torch/install/share/lua/5.1/torch/File.lua:409: in function 'load'
./utils/DataLoader.lua:47: in function 'create'
predict.lua:59: in main chunk
[C]: in function 'dofile'
.../torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: ?

Even if I donot use -gpuid parameter it gives the same error

Provided checkpoint file cannot be used.

Using the provided checkpoint with predict.

loading checkpoint from vqa_epoch23.49_0.5031.t7    
/root/torch/install/bin/luajit: /root/torch/install/share/lua/5.1/torch/File.lua:294: unknown object
stack traceback:
    [C]: in function 'error'
    /root/torch/install/share/lua/5.1/torch/File.lua:294: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:240: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:272: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    ...
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    /root/torch/install/share/lua/5.1/nngraph/gmodule.lua:402: in function 'read'
    /root/torch/install/share/lua/5.1/torch/File.lua:270: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:288: in function 'readObject'
    /root/torch/install/share/lua/5.1/torch/File.lua:319: in function 'load'
    predict.lua:63: in main chunk
    [C]: in function 'dofile'
    /root/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
    [C]: at 0x00406670

Also it says
To reproduce results shown on this page or try your own image-question pairs, download the following and run predict.lua with the appropriate paths.

What are the appropriate paths for answers_vocab.t7, questions_vocab.t7 and data.t7?

Btw training also doesn't work, i.e. the loss is nan:

Parameters: 6867121 
Batches: 3363   
Max iterations: 168150  
epoch 0.0029735355337496 loss nan
epoch 0.0059470710674993 loss nan   
epoch 0.0089206066012489 loss nan   
epoch 0.011894142134999 loss nan    
epoch 0.014867677668748 loss nan

work issue

Hello,

I didn't encounter any problems while running the example code, but the answers always come out as yes or no.

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?'

using CUDA on GPU 0...
Loading data files...
loading checkpoint from checkpoints/vqa_epoch23.26_0.4610.t7
Vocab size of checkpoint and data are different.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:537] Reading dangerously large protocol message. If the message turns out to be larger than 1073741824 bytes, parsing will be halted for security reasons. To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:78] The total number of bytes read was 574671192
Successfully loaded models/VGG_ILSVRC_19_layers.caffemodel
conv1_1: 64 3 3 3
conv1_2: 64 64 3 3
conv2_1: 128 64 3 3
conv2_2: 128 128 3 3
conv3_1: 256 128 3 3
conv3_2: 256 256 3 3
conv3_3: 256 256 3 3
conv3_4: 256 256 3 3
conv4_1: 512 256 3 3
conv4_2: 512 512 3 3
conv4_3: 512 512 3 3
conv4_4: 512 512 3 3
conv5_1: 512 512 3 3
conv5_2: 512 512 3 3
conv5_3: 512 512 3 3
conv5_4: 512 512 3 3
fc6: 1 1 25088 4096
fc7: 1 1 4096 4096
fc8: 1 1 4096 1000
yes

Do you have an idea how to solve the problem?

modify the code to do image caption

Based on your code, I think it is very natural and easy to modify it to do the task of image caption. Here is the version I implemented, but currently the implementation is flawed because the performance is bad. can U take some time to review it and give me some suggestions, here is the code link:
https://github.com/eriche2016/Image-caption-version2

Performance on VQA test set

Hi Abhishek,

Interesting project. Have you evaluated your model on the VQA test set? If yes, what accuracy did you obtain?

Thanks,
Avi Singh

cutorch not necessary for extracting image features on CPU

Great work and very informative accompanying readme file!

However, I think there is an issue in extracting image features using extract_fc7.lua on CPU.

extract_fc7.lua:123: attempt to index global 'cutorch' (a nil value)

I think this issue can be resolved by substituting line 123 cutorch.synchronize() by
if opt.gpuid >= 0 then cutorch.synchronize() end

Thanks!

what 's means about "not found: .......THNN.lua:108: NYI: call arg type " ?

rzai@rzai00:~/prj/neural-vqa$ CUDA_VISIBLE_DEVICES=0 th train.lua -gpuid 0
{
beta : 0.999
train_fc7_file : "data/train_fc7.t7"
embedding_size : 512
val_fc7_file : "data/val_fc7.t7"
dropout : 0.5
seed : 981723
data_dir : "data"
learning_rate_decay : 0.95
epsilon : 1e-08
learning_rate_decay_after : 15
max_epochs : 50
checkpoint_dir : "checkpoints"
rnn_size : 512
alpha : 0.8
num_layers : 2
init_from : ""
savefile : "vqa"
batch_size : 2
val_fc7_image_id_file : "data/val_fc7_image_id.t7"
train_fc7_image_id_file : "data/train_fc7_image_id.t7"
save_every : 1000
learning_rate : 0.0004
gpuid : 0
}
not found: THNN_CudaHalfELU_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfELU_updateGradInput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfHardTanh_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfHardTanh_updateGradInput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfLeakyReLU_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfLeakyReLU_updateGradInput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfLookupTable_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfLookupTable_renorm/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfMarginCriterion_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfMarginCriterion_updateGradInput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfMultiMarginCriterion_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfMultiMarginCriterion_updateGradInput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfPReLU_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSpatialConvolutionLocal_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSpatialConvolutionMM_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSpatialCrossMapLRN_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSpatialCrossMapLRN_updateGradInput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSpatialDilatedConvolution_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSpatialFullConvolution_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSoftPlus_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSoftPlus_updateGradInput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSoftShrink_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSoftShrink_updateGradInput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfSqrt_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfTemporalConvolution_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfThreshold_updateOutput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfThreshold_updateGradInput/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfVolumetricConvolution_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfVolumetricDilatedConvolution_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
not found: THNN_CudaHalfVolumetricFullConvolution_accGradParameters/home/rzai/torch/install/share/lua/5.1/nn/THNN.lua:108: NYI: call arg type
using CUDA on GPU 0...
Loading data files...
Loading train fc7 features from data/train_fc7.t7

LookupTable.lua:75: bad argument #3 to 'index' (Tensor | LongTensor expected, got torch.CudaLongTensor)

Error detail analysis:

$th train.lua -gpuid 0

using CUDA on GPU 0...
Loading data files...
Loading train fc7 features from data/train_fc7.t7
Loading val fc7 features from data/val_fc7.t7
Parameters: 6813673
Batches: 1076
Max iterations: 53800
/home/cse/torch/install/bin/luajit:
/home/cse/torch/install/share/lua/5.1/nn/Container.lua:67:
In 1 module of nn.Sequential:
/home/cse/torch/install/share/lua/5.1/nn/LookupTable.lua:75: bad argument
#3 to 'index' (Tensor | LongTensor expected, got torch.CudaLongTensor)

stack traceback:
[C]: in function 'index'
/home/cse/torch/install/share/lua/5.1/nn/LookupTable.lua:75: in
function
[C]: in function 'xpcall'
/home/cse/torch/install/share/lua/5.1/nn/Container.lua:63: in function
'rethrowErrors'
/home/cse/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function
'forward'
train.lua:375: in function 'opfunc'
/home/cse/torch/install/share/lua/5.1/optim/adam.lua:37: in function
'adam'
train.lua:476: in main chunk
[C]: in function 'dofile'
.../cse/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in
main chunk
[C]: at 0x00405970

WARNING: If you see a stack trace below, it doesn't point to the place
where this error occurred. Please use only the one above.
stack traceback:
[C]: in function 'error'
/home/cse/torch/install/share/lua/5.1/nn/Container.lua:67: in function
'rethrowErrors'
/home/cse/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function
'forward'
train.lua:375: in function 'opfunc'
/home/cse/torch/install/share/lua/5.1/optim/adam.lua:37: in function
'adam'
train.lua:476: in main chunk
[C]: in function 'dofile'
.../cse/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in
main chunk
[C]: at 0x00405970

Reffered : I have searched this problem and found following link :

https://groups.google.com/forum/#!topic/torch7/6igs4XdoSW4
jcjohnson/neural-style#210
jcjohnson/torch-rnn#56
https://groups.google.com/forum/#!topic/torch7/uEeBWwkyDPU

Solution : After ,I referred those link, i have re-installed following packages

luarocks install nn
luarocks install cunn
luarocks install cunn 1.0-0
luarocks install torch
luarocks install cutorch
luarocks install cutorch 1.0-0

But, I got same error. Please let me know how do i solve this issue.

cannot open <data/MultipleChoice_mscoco_train2014_questions.json> in mode r at /home/hadjer/torch/pkg/torch/lib/TH/THDiskFile.c:673 stack traceback: [C]: ? [C]: in function 'DiskFile' ./utils/DataLoader.lua:234: in function 'json_to_tensor' ./utils/DataLoader.lua:43: in function 'create' extract_fc7.lua:47: in main chunk [C]: in function 'dofile' .../torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk

cannot open <data/MultipleChoice_mscoco_train2014_questions.json> in mode r at /home/hadjer/torch/pkg/torch/lib/TH/THDiskFile.c:673
stack traceback:
[C]: ?
[C]: in function 'DiskFile'
./utils/DataLoader.lua:234: in function 'json_to_tensor'
./utils/DataLoader.lua:43: in function 'create'
extract_fc7.lua:47: in main chunk
[C]: in function 'dofile'
.../torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
Hello,
I had this problem when I installed lua5.1
could someone help to solve this issue plz

abhshkdz / neural-vqa Goto Github PK

neural-vqa's Introduction

neural-vqa

Setup

Known issues

Usage

Extract image features

Options

Training

Options

Testing

Options

Sample predictions

Implementation Details

Pretrained model and data files

References

License

neural-vqa's People

Contributors

Stargazers

Watchers

Forkers

neural-vqa's Issues

Recommend Projects

Recommend Topics

Recommend Org