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_0131)
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 | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 131 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7752 |
| Val Accuracy | 0.7629 |
| Test Accuracy | 0.7446 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, camel, mouse, sunflower, bowl, tank, lawn_mower, caterpillar, oak_tree, table, tiger, cattle, baby, television, road, couch, rose, possum, apple, tulip, lamp, mushroom, rocket, bicycle, leopard, poppy, palm_tree, snake, willow_tree, butterfly, pickup_truck, motorcycle, keyboard, dolphin, shark, cloud, cockroach, tractor, whale, bus, lobster, orchid, cup, rabbit, bee, dinosaur, orange, otter, forest, can