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_0065)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 65 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8852 |
| Val Accuracy | 0.8413 |
| Test Accuracy | 0.8560 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, baby, train, snail, tank, lamp, motorcycle, television, tulip, orchid, lizard, sunflower, flatfish, bear, squirrel, house, bed, bottle, sweet_pepper, skunk, boy, pickup_truck, tiger, mouse, ray, table, can, couch, seal, worm, cloud, elephant, poppy, caterpillar, chimpanzee, lobster, plain, fox, dinosaur, beaver, chair, lion, trout, apple, bicycle, aquarium_fish, spider, man, castle, bee