Sandy Chen

Let me download it and test it again ;)

Sorry I copied and pasted the wrong one!!! ``` python preprocess_MSCOCO_captions.py \ --input ../data/MSCOCO/yjcaptions26k_clean.json \ --output ../data/MSCOCO/yjcaptions26k_clean_processed.json \ --outdic ../data/MSCOCO/yjcaptions26k_clean_processed_dic.json \ --outfreq ../data/MSCOCO/yjcaptions26k_clean_processed_freq.json \ --cut 0 \ --char True \...

And the learning rate is nan if I run this command then train the model ;) Do you have any idea why this would happen? I will try to test...

Cool, i will do it later, and there is now another dataset for MSCOCO in Japanese: https://stair.center/archives/338, I will test it with the old dataset and the new dataset ;)