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_0770)
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 | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 770 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8304 |
| Val Accuracy | 0.8072 |
| Test Accuracy | 0.7990 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, dinosaur, kangaroo, cattle, cockroach, cup, poppy, chimpanzee, snail, keyboard, sweet_pepper, motorcycle, maple_tree, bowl, flatfish, boy, road, streetcar, tiger, castle, bicycle, crab, tractor, lobster, clock, dolphin, leopard, mushroom, skunk, rocket, skyscraper, raccoon, lion, hamster, tank, cloud, oak_tree, porcupine, chair, caterpillar, shrew, ray, can, willow_tree, crocodile, orange, rose, bee, baby, possum