karpathy / neuraltalk

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
5.4k stars 1.32k forks source link

How to generate json for new data? #13

Closed VanessaD closed 9 years ago

VanessaD commented 9 years ago

Hi Andrej, I was interested in using your algorithm for some new data. Basically, each images is associated with one sentence. Is there a convenient way to generate the json file as in your example (Flickr8k, etc). What is the structure of the json, and is there anyway to not using json format?

Thanks! Wei

karpathy commented 9 years ago

Hi, there isn't any explicit code for this. Look at the json's manually and inspect the DataProvider class. I think it's relatively simple so I didn't add any explicit utilities.