Downloads · 30 days
0
self-ensembling-resnet152
sueszli/self-ensembling-resnet152
self-ensembling-resnet152 is a machine learning model from sueszli. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
reproducing: "Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness" (https://arxiv.org/abs/2408.05446)
Access
Public
Updated Oct 15, 2024
Repo size
30.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth24.1 GB · 79%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Oct 1, 2024
- Updated
- Oct 15, 2024
- SHA
- 7ba1f3ba
Model card
From the Hugging Face model README
reproducing: "Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness" (https://arxiv.org/abs/2408.05446)
source code and usage examples: https://github.com/ETH-DISCO/self-ensembling
architecture based on Torchvision's Resnet152 default implementation
hyperparameters:
- criterion:
torch.nn.CrossEntropyLoss() - optimizer:
torch.optim.AdamW - scaler:
GradScaler - datasets:
["cifar10", "cirfar100"] - lr:
0.0001 - num_epochs:
16(higher would be even better, but maybe by <1%) - crossmax_k:
2(difference betweencrossmax_k=2andcrossmax_k=3is about 1-2%, so it's not a big deal)
- License
- apache-2.0
- Created
- Oct 1, 2024
- Updated
- Oct 15, 2024