search

aimagelab / meshed-memory-transformer

Meshed-Memory Transformer for Image Captioning. CVPR 2020
BSD 3-Clause "New" or "Revised" License
519 stars 136 forks source link

Performance without reinforce optimization stage #32

Open wdyin opened 4 years ago

wdyin commented 4 years ago

Hi,

Thanks for providing the implementation.

I checked the paper and observe that only performance with reinforce optimization is reported. I wonder if you can report the performance of your model before reinforce optimization stage.

Thanks.

Timon0327 commented 2 years ago

Hi,

Thanks for providing the implementation.

I checked the paper and observe that only performance with reinforce optimization is reported. I wonder if you can report the performance of your model before reinforce optimization stage.

Thanks.

Hi, did you just train the model without RL optimization? When I just train the transformer model withou RL optimization, the test CIDEr is very bad.