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_0284)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 284 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6453 |
| Val Accuracy | 0.6416 |
| Test Accuracy | 0.6264 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, couch, lamp, mouse, bowl, bridge, camel, lobster, raccoon, maple_tree, lizard, apple, castle, dolphin, beaver, rocket, crab, house, bottle, bed, dinosaur, cattle, palm_tree, spider, lion, train, bicycle, caterpillar, lawn_mower, pickup_truck, seal, fox, keyboard, leopard, skyscraper, possum, forest, pine_tree, woman, shrew, snake, pear, can, kangaroo, orchid, road, wardrobe, oak_tree, clock, bus