Closed hannahgym closed 1 year ago
using https://github.com/LisaAnne/ECCV2016/blob/master/utils/preprocess_captions.py I can generate
descriptions_bird.train_noCub.fg.json using train_noCub.txt
test.txt, val.txt train_noCub.txt are provided at https://drive.google.com/drive/folders/1nU9ATTLHAM6_jz-K6hoVlDzNrFcOXtyH (data.zip)
however, there is not any train.txt? what is train_noCub.txt? could you please help me in this regard?
It is a little bit late but maybe it helps others in the future: In the file cub-data-setup-linux.sh there is a line where this problem will be solved: https://github.com/salaniz/pytorch-gve-lrcn/blob/d1d9d29a96ce803cfb350ae77597434e67fefb57/cub-data-setup-linux.sh#L23 It is only a renaming of the _trainnoCub.txt to train.txt.
The cub-data-setup-linux.sh
script now uses the google drive resources to download and setup the data. It should create all the necessary files to run the code.
Could you please guide me where I can find the above json file?
/thanks