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_0419)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 419 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9755 |
| Val Accuracy | 0.8909 |
| Test Accuracy | 0.8850 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, dolphin, television, crocodile, can, pear, keyboard, spider, porcupine, man, castle, caterpillar, rabbit, lamp, palm_tree, cup, girl, flatfish, bowl, bear, baby, maple_tree, otter, shrew, fox, sunflower, lizard, motorcycle, bicycle, raccoon, woman, lion, cattle, rose, plate, kangaroo, whale, leopard, butterfly, forest, turtle, oak_tree, lawn_mower, bridge, sweet_pepper, hamster, skyscraper, willow_tree, plain, clock