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_0335)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 335 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9807 |
| Val Accuracy | 0.8896 |
| Test Accuracy | 0.8908 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, wolf, pine_tree, ray, can, camel, rose, bear, sweet_pepper, mountain, cockroach, girl, pear, lizard, raccoon, tank, sunflower, flatfish, streetcar, mouse, kangaroo, boy, skyscraper, dinosaur, forest, tractor, worm, bicycle, maple_tree, sea, lamp, cloud, shrew, plain, keyboard, shark, tiger, orange, chair, beetle, rabbit, squirrel, bowl, willow_tree, palm_tree, pickup_truck, oak_tree, train, baby, crab