Can not reproduce the result (both paper & yours)

[wizcheu]

I reran your code and the result seems not so good. My CIFAR_10(Wide-ResNet 28x10) result:

{   
    "loss_train": 0.46477456643031195,
    "loss_valid": 0.0,
    "loss_test": 0.10433908870220185,
    "top1_train": 0.8350560897435897,
    "top1_valid": 0.0,
    "top1_test": 0.9663,
    "top5_train": 0.971133814102564,
    "top5_valid": 0.0,
    "top5_test": 0.9991,
    "epoch": 200
}

Can you tell me your running environment like gpu nums & gpu device.

And one more questions, why the top1_train accuracy is so low.

[SwanseaLeo]

I have almost the same result as yours. { "loss_train": 0.4614731064209571, "loss_valid": 0.0, "loss_test": 0.09948565063476562, "top1_train": 0.8370192307692308, "top1_valid": 0.0, "top1_test": 0.9682, "top5_train": 0.9710336538461538, "top5_valid": 0.0, "top5_test": 0.9992, "epoch": 200 } @wizcheu

[JiyueWang]

I got similar results on CIFAR10. And on CIFAR100, the accuracy also 1% below the claimed 83.3%. Anyone success?
"model": { "type": "wresnet28_10" }, "dataset": "cifar100", "aug": "randaugment", "randaug": { "N": 2, "M": 14 }, "cutout": 16, "batch": 256, "epoch": 200, "lr": 0.1, "lr_schedule": { "type": "cosine", "warmup": { "multiplier": 2, "epoch": 5 } }, "optimizer": { "type": "sgd", "nesterov": true, "decay": 0.0005 }, "_version": 1, "_timestamp": "2020/11/26 15:36:12", "config": "confs/wresnet28x10_cifar100_b256.yaml", "tag": "", "dataroot": "data/private/pretrainedmodels", "save": "cifar100_wres28x10zz.pth\r", "cv": 0, "only": { "eval": false }

{ "loss_train": 1.5054243803024292, "loss_valid": 0.0, "loss_test": 0.6414522695541381, "top1_train": 0.655108173076923, "top1_valid": 0.0, "top1_test": 0.8185, "top5_train": 0.7444711538461538, "top5_valid": 0.0, "top5_test": 0.9638, "epoch": 195 }

[humza909]

Same here. Unable to reproduce this repo's results. Any success?