You can deploy this model and start earning money today!

vimarsh/
smart-repro-cifar100-resnet50

Name: smart-repro-cifar100-resnet50
Availability: InStock

Views

No views yet

ResNet-50 / CIFAR-100 (Mukhoti et al. recipe) — SMART reproduction backbone

Trained from scratch for the reproduction of Sample Margin-Aware Recalibration of Temperature Scaling (ICML 2026, OpenReview IkPdV0stxX), because the checkpoints the paper cites (Mukhoti et al. 2020) are not mirrored on the Hub.

Recipe (paper Sec. 4.1): 350 epochs, SGD momentum 0.9, weight decay 5e-4, LR 0.1 -> 0.01 -> 0.001 at 150/100/100 epochs, random crop(32, pad 4) + horizontal flip, batch 128, 45,000 train / 5,000 val / 10,000 test.

	value
test top-1	77.68%
val top-1	77.54%
uncalibrated ECE (15 bins)	10.02%
training time	2 h 9 min, 1x RTX 4000 Ada

Files: resnet50_cifar100.pt (state dict for official_repo_anon/models/resnet_cifar.py:ResNet50_CIFAR), logits_val.npz / logits_test.npz (logits + labels), split_indices.npz, train_history.json.

Logbook: https://huggingface.co/spaces/vimarsh/repro-sample-margin-aware-recalibration-of-temperature-scaling

vimarsh/smart-repro-cifar100-resnet50

ResNet-50 / CIFAR-100 (Mukhoti et al. recipe) — SMART reproduction backbone

vimarsh/
smart-repro-cifar100-resnet50