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_0536)
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 | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 536 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9551 |
| Val Accuracy | 0.8987 |
| Test Accuracy | 0.8924 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tractor, orchid, rocket, beetle, tiger, caterpillar, clock, bowl, bed, forest, aquarium_fish, girl, sweet_pepper, tank, dinosaur, pine_tree, palm_tree, kangaroo, lobster, lion, ray, boy, orange, house, worm, wolf, crab, lawn_mower, chimpanzee, tulip, rabbit, train, trout, possum, raccoon, sea, sunflower, plain, bear, dolphin, baby, cockroach, wardrobe, lamp, telephone, porcupine, leopard, snail, crocodile, lizard