Closed dschaehi closed 2 years ago
Hi @dschaehi I have uploaded the annotations file. Please see the README.md. Sorry that I forgot to upload them.
Regards
Hi @fawazsammani,
Thank you for your reply! The code works so far.
By the way, for coco caption I had to follow the setup procedure (i.e.., downloading Stanford CoreNLP 3.6.0 and Google News negative 300 word2vec model) to correctly install it. This is missing in the current README.md
of this repo. Perhaps you can consider including it.
@dschaehi Google News negative 300 word2vec model is only required for WMD, which we do not use. As for Stanford CoreNLP, the instructions are already in the cococaption repo.
Regards
@fawazsammani Yes, but based on the current README.md
I was only required to download coco caption and put it in the cococaption
folder. I took this instruction "literally" (i.e., I just downloaded it) and did not try to follow the installation guideline in the coco caption repo. Maybe it was my fault.
By the way, without the Google News negative 300 word2vec model I got the error message below. So I had to download it with the script provided by the coco caption repo.
FileNotFoundError: [Errno 2] No such file or directory: '/data/lee/home/Projects/nlxgpt/cococaption/pycocoevalcap/wmd/data/GoogleNews-vectors-negative300.bin'
@dschaehi you have to also comment out the line: from .wmd.wmd import WMD
in the script coco-caption/pycocoevalcap/eval.py
. But nevermind if you already installed it.
Regards
@fawazsammani Thanks for the tip. I am currently trying to reproduce the results on the paper. I'll let you know if there is any issue.
Hi @fawazsammani,
Thank you for the sharing the code! I have a little issue in training the model on VQA-X. The training script complains that file
cococaption/annotations/vqaX_test_annot_exp.json
is missing. Indeed there is no such a file in that folder (cf.~https://github.com/ruotianluo/coco-caption/tree/ea20010419a955fed9882f9dcc53f2dc1ac65092/annotations). Could you help me with this issue? Thank you.Below is the full error message: