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_0684)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 684 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9747 |
| Val Accuracy | 0.8877 |
| Test Accuracy | 0.8914 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, crab, cockroach, mountain, bottle, girl, ray, bowl, crocodile, maple_tree, elephant, keyboard, seal, poppy, skyscraper, snail, shrew, cattle, squirrel, mouse, raccoon, road, motorcycle, pear, trout, plate, rocket, bear, rabbit, hamster, couch, boy, fox, television, lawn_mower, leopard, aquarium_fish, bed, porcupine, beaver, tractor, telephone, castle, wardrobe, otter, worm, tiger, rose, butterfly, camel