GoodNews

GoodNews copied to clipboard

Hello, I've been studying dataloader.py recently, and I have a question about line 260 in your code: self.info['images'][i]['id']. I don't understand it and feel like it doesn't contribute to shuffling....

yueryaa

Epochs of running

1

How many epochs should I run your code with to get the result published in your paper?

tristan199714

Will a pre-trained model be released?

lucassheldonstr

No such file or directory: '../resized/resized/51cf8b8d7e0d9c0839d2d1b1_1.jpg'

1

Getting this error when running prepro_images. This is not in the google drive archive with all the resized pictures that is provided.

devdev999

ValueError: u'59248f9895d0e024b5872783' is not in list when training

3

I encounter this when trying to train: Traceback (most recent call last): File "train.py", line 283, in train(opt) File "train.py", line 139, in train data = loader.get_batch('train') File "/im2p/GoodNews-master/dataloader.py", line...

devdev999

Dear author, thank you for your contribution. Where can i get "data_news.json", Thank you for your reply

liuxiaoliu321

Hi, You seem to just extracted a part of the text as an ‘’ article ’’ in captioning_dataset.json, how did you select?

jiasureZ

Have attached traceback, am not sure what is calling this error. Traceback (most recent call last): File "train.py", line 283, in train(opt) File "train.py", line 173, in train out =...

devdev999

Hi and thanks for providing this repo, when I use "prepro_images.py", the results show lacking of picture 58cedcaa95d0e02489b91f23_4.jpg, the picture name is show in data_news.json, which is not in img_urls_all.json...

ChenTao2017110

Hi and thanks for providing this repo, maybe related to [#6](https://github.com/furkanbiten/GoodNews/issues/6), it seems the files do not use the same indices: ``` urls = json.load(open('img_urls_all.json','r')) capt = json.load(open('../../data/captioning_dataset.json','r')) print(capt['58cedcaa95d0e02489b91f23']['images']) {'0':...

pgaylumen