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_0197)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 197 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9902 |
| Val Accuracy | 0.9256 |
| Test Accuracy | 0.9142 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, table, motorcycle, telephone, dolphin, streetcar, trout, maple_tree, road, cloud, mountain, snail, mouse, lawn_mower, beetle, tulip, lion, television, flatfish, crab, fox, lobster, bicycle, spider, tank, turtle, caterpillar, cup, orange, beaver, couch, man, kangaroo, tiger, porcupine, chair, bottle, keyboard, crocodile, can, sweet_pepper, castle, leopard, worm, lizard, hamster, wolf, camel, plate, rocket