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_0903)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 903 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8884 |
| Val Accuracy | 0.8360 |
| Test Accuracy | 0.8326 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, bowl, cloud, motorcycle, tulip, porcupine, pine_tree, shrew, table, rose, dinosaur, baby, fox, hamster, crocodile, sweet_pepper, raccoon, man, plate, caterpillar, telephone, leopard, beaver, bottle, streetcar, couch, crab, worm, can, castle, road, tractor, chair, wardrobe, bear, aquarium_fish, house, skunk, trout, forest, rocket, cup, flatfish, pear, bed, cockroach, tank, shark, girl, lobster