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_0010)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 10 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5782 |
| Val Accuracy | 0.5501 |
| Test Accuracy | 0.5736 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mountain, bee, aquarium_fish, sunflower, plain, chimpanzee, trout, beetle, table, pear, possum, baby, fox, dinosaur, boy, crocodile, squirrel, bridge, pine_tree, bus, television, raccoon, crab, camel, lizard, bear, snail, tiger, motorcycle, butterfly, cockroach, telephone, pickup_truck, girl, house, poppy, road, orchid, bottle, can, caterpillar, bicycle, rabbit, kangaroo, castle, hamster, keyboard, mushroom, mouse, wolf