Igor Kasianenko

Results 2 issues of Igor Kasianenko

I have trained model using timm distributed_train.sh, but I have 0.1 validation accuracy on imagenet. Images in validation folder are all placed in root directory going like `ILSVRC2012_val_00000001.JPEG ... ILSVRC2012_val_00050000.JPEG`....

enhancement

Hello, are you going to add GPU support? It looks like main.py train doesn't utilize GPU