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_0076)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 76 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9393 |
| Val Accuracy | 0.8797 |
| Test Accuracy | 0.8652 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, pear, beaver, porcupine, bicycle, leopard, orange, couch, tiger, road, bus, mouse, crab, train, lizard, lobster, television, boy, plate, possum, house, lamp, whale, crocodile, seal, sunflower, hamster, bowl, camel, mountain, turtle, orchid, raccoon, tulip, dinosaur, wardrobe, baby, tank, tractor, bed, table, poppy, willow_tree, aquarium_fish, telephone, pine_tree, can, castle, caterpillar, palm_tree