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_0389)
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 | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 389 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9829 |
| Val Accuracy | 0.8920 |
| Test Accuracy | 0.8894 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, spider, bridge, crocodile, squirrel, flatfish, turtle, dinosaur, bee, sea, pine_tree, plain, mushroom, cup, bed, caterpillar, baby, bottle, road, cattle, beaver, motorcycle, skyscraper, cloud, leopard, cockroach, bus, beetle, ray, mouse, lion, rose, tiger, orchid, poppy, boy, couch, wardrobe, whale, crab, rabbit, porcupine, willow_tree, apple, snake, rocket, skunk, lobster, camel, lizard