SUN's H

[Xiao-lv-lol]

Hello, the H I got on SUN by using the parameters you provided and the method in the paper is 2% less than the result in your paper, I wonder if you have encountered such a situation. Could you please provide SUN's training parameters again? --dataset SUN
--class_embedding att
--syn_num 100
--batch_size 1024
--attSize 102
--nz 102
--embedSize 2048
--outzSize 512
--nhF 1024
--ins_weight 0.01
--cls_weight 0.01
--ins_temp 0.1
--cls_temp 0.1
--manualSeed 4115
--nclass_all 717
--nclass_seen 645
--gpus 1
--lr_decay_epoch 100
--lr 0.00005‘

[via815via]

I have the same problem. My paramters is same as yours. Do you solve this problem?

[Hanzy1996]

SUN needs more epoch training, about 1,000 epochs. Please refer to the updated hyper-parameters.