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_0300)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 300 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5923 |
| Val Accuracy | 0.5712 |
| Test Accuracy | 0.5780 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, castle, possum, trout, beaver, streetcar, elephant, train, pine_tree, skyscraper, clock, wolf, snake, forest, lawn_mower, bridge, skunk, road, seal, tiger, worm, spider, orange, raccoon, flatfish, motorcycle, sweet_pepper, boy, rabbit, squirrel, chair, plate, kangaroo, snail, girl, bee, bicycle, otter, ray, table, keyboard, couch, fox, telephone, turtle, bus, tractor, palm_tree, sunflower, dinosaur