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_0237)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 237 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7445 |
| Val Accuracy | 0.7352 |
| Test Accuracy | 0.7250 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, oak_tree, mouse, spider, bottle, table, clock, snake, willow_tree, baby, rabbit, beetle, orange, man, hamster, bus, sunflower, leopard, raccoon, bridge, lizard, rose, house, cockroach, motorcycle, whale, sea, shrew, tank, fox, cup, mountain, pear, skunk, wolf, pine_tree, shark, girl, squirrel, chimpanzee, seal, forest, kangaroo, bowl, telephone, wardrobe, maple_tree, castle, worm, dinosaur