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_0208)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 208 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9401 |
| Val Accuracy | 0.8704 |
| Test Accuracy | 0.8626 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, camel, apple, telephone, castle, cockroach, rose, girl, spider, porcupine, crocodile, squirrel, ray, rocket, caterpillar, plain, cup, train, oak_tree, whale, forest, butterfly, mouse, poppy, motorcycle, lawn_mower, dinosaur, bear, otter, bottle, lobster, clock, baby, palm_tree, snake, table, aquarium_fish, fox, dolphin, rabbit, tractor, bee, kangaroo, turtle, cattle, pine_tree, worm, boy, woman, snail