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_0448)
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 | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 448 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8198 |
| Val Accuracy | 0.8107 |
| Test Accuracy | 0.8016 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, lion, possum, snake, flatfish, skyscraper, maple_tree, bridge, cattle, television, sunflower, turtle, beetle, lawn_mower, bear, road, tank, squirrel, worm, butterfly, couch, cockroach, orange, keyboard, dolphin, rocket, skunk, man, caterpillar, hamster, spider, fox, tractor, train, leopard, shrew, clock, whale, wardrobe, chair, beaver, bottle, forest, snail, boy, poppy, pine_tree, lizard, crocodile, apple