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_0740)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 740 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9547 |
| Val Accuracy | 0.8749 |
| Test Accuracy | 0.8750 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, trout, snake, hamster, kangaroo, bicycle, sunflower, wolf, crab, skyscraper, fox, cup, pear, bus, maple_tree, palm_tree, rose, train, bed, squirrel, pine_tree, telephone, oak_tree, motorcycle, beaver, orchid, boy, flatfish, streetcar, cloud, poppy, possum, elephant, house, ray, sea, mouse, dinosaur, crocodile, spider, rocket, pickup_truck, seal, lobster, raccoon, wardrobe, mountain, forest, camel, shark