expected performance on `train-val` set

imatge-upc / rvos

RVOS: End-to-End Recurrent Network for Video Object Segmentation (CVPR 2019)

https://imatge-upc.github.io/rvos/

Other

277 stars 54 forks source link

expected performance on `train-val` set #6

Closed ZENGXH closed 5 years ago

ZENGXH commented 5 years ago

Hi,

Thanks so much for releasing the code and the splitting of the training set. Can I ask if you have test the performance of eval_provious_mask + the youtubevos-one-shot model you released + validation set in train-val-meta.json? I just want to double check if my testing is bug free.

Thanks!

carlesventura commented 5 years ago

Sorry but on the validation set (train-val) we only measured the loss, which is based on the Jaccard, but not the official evaluation measures. All models have been evaluated using the official evaluation server from either DAVIS or YouTube-VOS. We have not implemented the evaluation scripts.