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_0706)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 706 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9809 |
| Val Accuracy | 0.9077 |
| Test Accuracy | 0.9106 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tiger, bridge, snail, pickup_truck, bed, squirrel, plate, seal, bicycle, streetcar, spider, table, porcupine, whale, mushroom, fox, dolphin, tank, tractor, television, lamp, orange, bowl, chimpanzee, cup, bus, raccoon, lizard, lion, orchid, mountain, otter, elephant, lawn_mower, can, rose, wardrobe, woman, lobster, sunflower, crocodile, leopard, bottle, oak_tree, rabbit, snake, house, apple, road, caterpillar