xhzhao

@idansc Thank you, i fixed this code bug, and download the pretrained model from here(https://filebox.ece.vt.edu/~jiasenlu/codeRelease/co_atten/model/vqa_model/model_alternating_train-val_vgg.t7). I submitted the result with the name: vqa_OpenEnded_mscoco_test-dev2015_HieCoAttenVQA_results.json, and i got the accuracy like this:...

yeah, the json is provided, and the h5 file is generated by myself: 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

@idansc any idea about how to fix this misalignment problem?

I have tried to use GPU(M40) to train this model, but the training process is very slow(12.5 hour / 1 epoch, 250epoch is used in the paper), and i'm trying...

yes, it should be. I trained another model based on another github and the speed is very fast, while the accuracy is not good enough: [here](https://github.com/VT-vision-lab/VQA_LSTM_CNN/issues/28). I will double check...

@YauhenMinsk I don't know, because i did not reach the target accuracy on the repo. I suggest you to use this file: https://github.com/VT-vision-lab/VQA_LSTM_CNN/blob/master/eval.lua , and i got the target accuracy...