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_0836)
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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 836 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9480 |
| Val Accuracy | 0.8752 |
| Test Accuracy | 0.8824 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, snail, motorcycle, plain, possum, maple_tree, pear, mushroom, palm_tree, oak_tree, cattle, skyscraper, fox, mouse, skunk, tank, spider, keyboard, bicycle, girl, train, tractor, lawn_mower, mountain, rabbit, leopard, boy, dinosaur, rose, aquarium_fish, worm, road, orange, bowl, lamp, bear, poppy, streetcar, lizard, bus, woman, whale, crab, squirrel, beaver, cloud, pickup_truck, forest, seal, elephant