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_0052)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 52 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8910 |
| Val Accuracy | 0.8611 |
| Test Accuracy | 0.8614 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wolf, dolphin, bottle, couch, road, woman, streetcar, orange, trout, clock, rabbit, keyboard, pine_tree, bed, bicycle, camel, forest, poppy, cloud, bridge, apple, whale, pear, sunflower, house, chimpanzee, oak_tree, beetle, orchid, aquarium_fish, raccoon, castle, skyscraper, elephant, boy, sweet_pepper, lawn_mower, tank, bowl, palm_tree, lamp, worm, crocodile, snake, leopard, squirrel, mushroom, plain, train, kangaroo