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_0611)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 611 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9482 |
| Val Accuracy | 0.8856 |
| Test Accuracy | 0.8770 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
flatfish, table, telephone, lamp, apple, plain, sunflower, turtle, lobster, mountain, whale, bus, baby, ray, rocket, girl, fox, rabbit, possum, orange, couch, bear, plate, orchid, house, maple_tree, cockroach, pear, snake, raccoon, elephant, tulip, willow_tree, forest, sweet_pepper, butterfly, aquarium_fish, lizard, skyscraper, television, spider, mouse, keyboard, motorcycle, chimpanzee, tiger, cup, camel, lion, castle