Modelpublic

ProbeX/Model-JResNetmodel_idx_0579

sourceHugging Faceupdated 7mo agoView on Hugging Face

0likes23downloads

Model Card

Model-J: ResNet Model (modelidx0579)

This model is part of the Model-J dataset, introduced in:

Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz, Bar Cavia, Jonathan Kahana*, Yedid Hoshen

<p align="center"> 🌐 <a href="https://horwitz.ai/probex" target="blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="blank">Dataset</a> </p>

ProbeX

Model Details

Attribute	Value
Subset	ResNet
Split	train
Base Model	`microsoft/resnet-101`
Dataset	CIFAR100 (50 classes)

Training Hyperparameters

Parameter	Value
Learning Rate	3e-05
LR Scheduler	linear
Epochs	9
Max Train Steps	2997
Batch Size	64
Weight Decay	0.005
Seed	579
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.8106
Val Accuracy	0.7843
Test Accuracy	0.7872

Training Categories

The model was fine-tuned on the following 50 CIFAR100 classes:

beaver, trout, tulip, man, wolf, crab, flatfish, tractor, squirrel, motorcycle, pickup_truck, tank, bee, road, bottle, plate, clock, dolphin, skyscraper, otter, mouse, oak_tree, lizard, cockroach, maple_tree, rocket, seal, mountain, can, chimpanzee, shrew, leopard, worm, ray, orange, castle, hamster, bus, pine_tree, chair, forest, aquarium_fish, possum, bicycle, lawn_mower, orchid, dinosaur, kangaroo, plain, raccoon