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_0793)
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 | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 793 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7623 |
| Val Accuracy | 0.7387 |
| Test Accuracy | 0.7434 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, rabbit, couch, bee, bus, mountain, mushroom, shrew, woman, flatfish, seal, dolphin, bicycle, dinosaur, castle, caterpillar, man, leopard, raccoon, train, beaver, bridge, chair, whale, lobster, wolf, aquarium_fish, motorcycle, willow_tree, maple_tree, skyscraper, trout, boy, beetle, table, keyboard, baby, plain, tank, rose, porcupine, television, orange, cattle, fox, otter, tiger, cloud, worm, snake