zlyi1225

could you provide the methods how to prepare the 1.3M extra JFT images? What's the domain-relevance data filtering method mentioned in paper?

I found that even finetune from ImageNet pretrain, the loss grows up. I used the ResNet-vd as the baseline arch, and add GC-Block in. I also double check the performance...

When I build the solution first time with all default settings, it appears that "Error 298 error C2146: syntax error : missing ';' before identifier 'curandOrdering_t' C:\Program Files\NVIDIA GPU Computing...