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_0886)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 886 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8706 |
| Val Accuracy | 0.8336 |
| Test Accuracy | 0.8190 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, porcupine, plain, possum, lobster, raccoon, bowl, mushroom, sweet_pepper, apple, television, oak_tree, tractor, cattle, poppy, wardrobe, clock, motorcycle, fox, tank, worm, trout, castle, keyboard, telephone, lamp, butterfly, seal, maple_tree, rose, squirrel, woman, mountain, spider, shrew, ray, elephant, leopard, aquarium_fish, bed, mouse, road, lawn_mower, cockroach, bear, can, bicycle, house, shark, beaver