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_0367)
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 | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 367 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9006 |
| Val Accuracy | 0.8565 |
| Test Accuracy | 0.8544 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, bridge, table, cattle, bicycle, lion, television, wolf, sunflower, tulip, aquarium_fish, orange, keyboard, forest, leopard, bed, ray, lamp, cockroach, baby, girl, turtle, plain, dinosaur, bear, oak_tree, snail, cloud, trout, pine_tree, snake, mushroom, chimpanzee, man, beetle, tiger, shrew, clock, dolphin, fox, seal, house, sweet_pepper, couch, poppy, caterpillar, tractor, lobster, can, pear