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_0723)
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 |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 723 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9042 |
| Val Accuracy | 0.8589 |
| Test Accuracy | 0.8604 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, rabbit, table, chimpanzee, plain, telephone, train, rose, bee, cloud, motorcycle, baby, elephant, shark, television, bottle, raccoon, mushroom, skunk, tractor, oak_tree, turtle, ray, bowl, lawn_mower, crab, sweet_pepper, beaver, camel, cockroach, wolf, lobster, forest, can, lion, otter, beetle, skyscraper, squirrel, cup, orchid, palm_tree, couch, snail, orange, willow_tree, plate, house, crocodile, worm