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_0283)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 283 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9980 |
| Val Accuracy | 0.8936 |
| Test Accuracy | 0.8888 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, worm, maple_tree, boy, orchid, oak_tree, lion, rabbit, road, whale, crab, can, willow_tree, man, possum, crocodile, telephone, table, bear, lawn_mower, caterpillar, otter, wolf, beetle, orange, bus, shrew, palm_tree, lobster, elephant, kangaroo, bicycle, shark, tiger, bridge, television, snake, flatfish, chimpanzee, poppy, skunk, forest, mushroom, streetcar, pear, bowl, dolphin, seal, porcupine, sea