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_0537)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 537 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9488 |
| Val Accuracy | 0.8765 |
| Test Accuracy | 0.8774 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
caterpillar, train, bottle, cockroach, plate, hamster, mouse, worm, beaver, bridge, pear, crocodile, lamp, mountain, lion, orchid, dinosaur, lawn_mower, shark, seal, kangaroo, couch, sunflower, tiger, tulip, keyboard, turtle, elephant, butterfly, poppy, tank, bus, motorcycle, wardrobe, bicycle, willow_tree, fox, house, leopard, snake, bed, baby, plain, cloud, raccoon, sea, table, orange, maple_tree, chair