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_0023)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 23 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9724 |
| Val Accuracy | 0.9048 |
| Test Accuracy | 0.8918 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, pear, wolf, fox, trout, crocodile, orchid, mouse, cup, snail, turtle, bear, rabbit, rose, possum, porcupine, keyboard, elephant, train, poppy, television, raccoon, flatfish, maple_tree, camel, road, cloud, willow_tree, lion, worm, pine_tree, ray, table, dinosaur, wardrobe, dolphin, orange, cattle, chair, lizard, tank, castle, girl, tulip, butterfly, tiger, spider, kangaroo, lamp, streetcar