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_0135)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 135 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9885 |
| Val Accuracy | 0.8875 |
| Test Accuracy | 0.8908 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
road, table, forest, baby, lizard, television, cloud, dinosaur, whale, sweet_pepper, lion, snail, orchid, plain, hamster, train, leopard, otter, streetcar, trout, shrew, dolphin, house, bridge, cup, lobster, tiger, possum, wardrobe, sunflower, pine_tree, tractor, chimpanzee, bear, bowl, rocket, flatfish, crocodile, palm_tree, porcupine, willow_tree, kangaroo, camel, maple_tree, motorcycle, squirrel, seal, bottle, crab, boy