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_0543)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 543 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8514 |
| Val Accuracy | 0.8099 |
| Test Accuracy | 0.8132 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, willow_tree, telephone, bear, lawn_mower, oak_tree, train, tank, spider, tulip, caterpillar, bowl, rose, cloud, dinosaur, cattle, cup, fox, boy, bicycle, baby, bee, wolf, poppy, hamster, snake, porcupine, apple, rocket, can, elephant, otter, lizard, chimpanzee, forest, rabbit, orchid, worm, pear, plain, kangaroo, tractor, bridge, man, orange, girl, couch, dolphin, television, camel