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_0165)
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 | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 165 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9828 |
| Val Accuracy | 0.8856 |
| Test Accuracy | 0.8922 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, bowl, keyboard, seal, bear, bridge, sunflower, possum, tractor, cloud, tulip, mushroom, woman, wolf, crab, cup, otter, shrew, snail, forest, caterpillar, porcupine, pine_tree, mountain, lizard, castle, sea, apple, bee, chair, couch, baby, orchid, lamp, bottle, tiger, shark, lawn_mower, mouse, lion, streetcar, maple_tree, dinosaur, tank, dolphin, ray, flatfish, snake, beetle, kangaroo