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_0792)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 792 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8814 |
| Val Accuracy | 0.8387 |
| Test Accuracy | 0.8406 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
ray, bed, otter, seal, cattle, couch, possum, mushroom, squirrel, flatfish, elephant, house, rocket, caterpillar, poppy, bicycle, bee, bridge, tractor, camel, road, mouse, dinosaur, snail, lobster, willow_tree, plate, tiger, sweet_pepper, pickup_truck, turtle, raccoon, girl, orange, cloud, castle, boy, streetcar, spider, kangaroo, whale, can, bear, motorcycle, lion, butterfly, sunflower, palm_tree, cockroach, lawn_mower