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_0905)
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 | 0.01 |
| Seed | 905 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9941 |
| Val Accuracy | 0.9107 |
| Test Accuracy | 0.9078 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, porcupine, television, bottle, otter, tiger, turtle, pickup_truck, bear, raccoon, bus, beetle, worm, butterfly, telephone, clock, forest, maple_tree, hamster, flatfish, chair, lizard, plate, pear, snake, plain, lawn_mower, woman, spider, cup, aquarium_fish, poppy, mountain, house, shark, mouse, bowl, keyboard, tulip, cloud, girl, caterpillar, orange, skyscraper, willow_tree, ray, whale, tank, mushroom, train