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_0500)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 500 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9568 |
| Val Accuracy | 0.8709 |
| Test Accuracy | 0.8662 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
poppy, can, lawn_mower, oak_tree, rabbit, house, sweet_pepper, cloud, plate, tank, lizard, possum, motorcycle, baby, butterfly, leopard, cockroach, snake, pickup_truck, porcupine, chimpanzee, spider, shrew, fox, tulip, shark, apple, rose, bed, skyscraper, bear, pear, wolf, lamp, sunflower, clock, couch, streetcar, camel, castle, dinosaur, forest, bee, lobster, mushroom, ray, woman, rocket, plain, caterpillar