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_0639)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 639 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9040 |
| Val Accuracy | 0.8576 |
| Test Accuracy | 0.8466 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, bicycle, bowl, sunflower, plain, mouse, bed, lion, cloud, dolphin, porcupine, woman, rose, castle, palm_tree, cup, bottle, bridge, fox, possum, flatfish, wardrobe, girl, motorcycle, lizard, tiger, keyboard, mountain, chair, forest, willow_tree, kangaroo, telephone, lobster, lawn_mower, tractor, lamp, poppy, beetle, beaver, ray, rocket, apple, shark, aquarium_fish, dinosaur, turtle, raccoon, bee, streetcar