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_0015)
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 | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 15 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9369 |
| Val Accuracy | 0.8776 |
| Test Accuracy | 0.8724 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, raccoon, wolf, bed, mouse, shark, couch, squirrel, mushroom, motorcycle, television, house, caterpillar, porcupine, bottle, chair, lawn_mower, girl, sea, chimpanzee, possum, bee, trout, forest, beaver, sweet_pepper, snake, castle, tank, bowl, seal, turtle, cockroach, telephone, man, lion, sunflower, oak_tree, butterfly, rocket, bridge, baby, apple, train, bus, ray, lobster, bear, willow_tree, wardrobe