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_0350)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 350 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9730 |
| Val Accuracy | 0.8829 |
| Test Accuracy | 0.8894 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, girl, chimpanzee, orchid, motorcycle, mouse, mountain, bicycle, mushroom, cloud, trout, bee, tank, sunflower, couch, crab, elephant, bed, lawn_mower, house, bottle, willow_tree, plate, train, bridge, dinosaur, road, sea, fox, raccoon, palm_tree, hamster, butterfly, apple, squirrel, streetcar, flatfish, crocodile, lion, snail, seal, porcupine, rose, castle, clock, dolphin, beaver, woman, lobster, kangaroo