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_0215)
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 | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 215 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9869 |
| Val Accuracy | 0.8952 |
| Test Accuracy | 0.8796 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tiger, bowl, porcupine, elephant, table, mountain, can, beaver, sunflower, house, sweet_pepper, bear, turtle, oak_tree, wardrobe, willow_tree, television, shark, bee, man, poppy, tulip, maple_tree, boy, mushroom, cockroach, lawn_mower, trout, palm_tree, streetcar, butterfly, chimpanzee, bicycle, caterpillar, dinosaur, pear, flatfish, rocket, cup, squirrel, beetle, chair, baby, lobster, raccoon, crocodile, whale, snake, otter, tractor