google-research/augmix
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
PythonApache-2.0
Issues
- 1
- 1
- 0
none
#26 opened by Try1234567 - 0
Use combined with Object Detection
#24 opened by ver0z - 0
command for imagenet evaluation
#23 opened by Sarimuko - 2
- 1
KL divergenve
#17 opened by MADONOKOUKI - 2
Jensen–Shannon divergence
#20 opened by LamyaMohaned - 3
augmentations used in augmix
#22 opened by kiranchari - 5
- 2
mean and std for every channel is 0.5 instead of (0.5071, 0.4867. 0.4408) as mean and (0.2657, 0.2565, 0.2761) as std
#19 opened by shashankskagnihotri - 3
Issue loading pretrained weights
#18 opened by humzaiqbal - 1
Repeated Evaluation in ImageNet
#9 opened by LeeDoYup - 2
`depth` is constant each `width`
#13 opened by yumion - 2
There is a big gap between the results of the code and the results in the paper on CIFAR10-C
#15 opened by LinusWu - 4
Testing with the best model
#8 opened by LeeDoYup - 2
A question in "third_party/WideResNet_pytorch/wideresnet.py out = self.relu2(self.bn2(self.conv1(out)))
#12 opened by longlongvip - 0
Reproduce of Baseline
#11 opened by LeeDoYup - 3
- 1
- 2
CIFAR-10/ImageNet-P code
#5 opened by moskomule - 1
The CIFAR-10-C dataset are not normalized
#4 opened by Newbeeyoung - 3
ImageNet hparams
#3 opened by rwightman - 2
I found an error
#2 opened by minjieharmo - 1
About the loss function
#1 opened by WdBlink