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_0263)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 263 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9874 |
| Val Accuracy | 0.8824 |
| Test Accuracy | 0.8844 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, table, orchid, seal, lizard, rabbit, skyscraper, worm, turtle, bottle, rose, motorcycle, train, crab, forest, man, tractor, dolphin, raccoon, lamp, willow_tree, tulip, whale, lobster, wolf, butterfly, pear, beaver, plate, chimpanzee, camel, television, cockroach, porcupine, possum, shark, apple, rocket, poppy, kangaroo, fox, sweet_pepper, flatfish, sea, tank, bridge, bicycle, hamster, streetcar, mountain