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_0933)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 933 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8196 |
| Val Accuracy | 0.7909 |
| Test Accuracy | 0.7900 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, table, boy, bee, skyscraper, lobster, mushroom, tractor, bicycle, road, kangaroo, sunflower, worm, poppy, mouse, beetle, man, oak_tree, seal, cattle, raccoon, hamster, whale, snail, lamp, apple, motorcycle, caterpillar, pine_tree, dinosaur, cup, turtle, streetcar, pear, tulip, butterfly, skunk, chair, orange, telephone, beaver, mountain, palm_tree, shark, chimpanzee, orchid, pickup_truck, house, clock, plain