metadata
base_model: microsoft/resnet-101
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: ResNet Model (model_idx_0044)
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
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
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 | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 44 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8891 |
| Val Accuracy | 0.8547 |
| Test Accuracy | 0.8556 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
telephone, willow_tree, television, snail, pear, boy, road, trout, woman, butterfly, cup, motorcycle, bear, tractor, pickup_truck, beetle, house, bottle, orchid, leopard, crab, poppy, baby, spider, sweet_pepper, forest, lizard, lawn_mower, rabbit, apple, cloud, wardrobe, cockroach, bowl, lamp, castle, maple_tree, streetcar, clock, rose, fox, train, mushroom, possum, shark, bicycle, worm, bee, skunk, mountain