Closed ZENGXH closed 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.
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
+ theyoutubevos-one-shot
model you released + validation set intrain-val-meta.json
? I just want to double check if my testing is bug free.Thanks!