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_0590)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 590 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9974 |
| Val Accuracy | 0.9048 |
| Test Accuracy | 0.9014 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, clock, plate, television, crocodile, castle, leopard, dolphin, whale, trout, worm, mountain, flatfish, bicycle, lamp, girl, pear, tulip, otter, turtle, forest, bus, wolf, beaver, orchid, skyscraper, house, plain, beetle, elephant, tiger, crab, hamster, camel, spider, telephone, porcupine, apple, snail, orange, chair, streetcar, cloud, mushroom, can, pickup_truck, train, shrew, lawn_mower, seal