search

jcjohnson / densecap

Dense image captioning in Torch
MIT License
1.58k stars 429 forks source link

training on new datasets of 100 random images. #91

Open aiwithshekhar opened 5 years ago

aiwithshekhar commented 5 years ago

Screenshot from 2019-05-02 21-51-29 I thought of training on 100 random images to check whether own training can be done, but i got this error of split is empty?. I have uploaded an image of the error, if the error is because my small dataset can you please help with required changes. Also is it required to modify below:- 1) discard all images that have fewer than 20 or more than 50 annotations. 2)assign 5,000 each to val/test splits and the rest to train.