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_0909)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 909 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9827 |
| Val Accuracy | 0.8883 |
| Test Accuracy | 0.8846 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, shrew, willow_tree, lawn_mower, plate, squirrel, butterfly, cattle, clock, television, turtle, lamp, girl, couch, mushroom, lobster, elephant, bowl, bear, beaver, dolphin, forest, bed, telephone, mountain, beetle, pickup_truck, wolf, tank, bicycle, house, motorcycle, bee, seal, apple, wardrobe, baby, lion, sweet_pepper, train, shark, rabbit, skyscraper, spider, hamster, whale, lizard, tractor, leopard, porcupine