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_0383)
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 | 9e-05 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 383 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9800 |
| Val Accuracy | 0.8824 |
| Test Accuracy | 0.8772 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beaver, raccoon, house, forest, woman, tiger, crocodile, turtle, fox, sweet_pepper, bowl, flatfish, sunflower, lobster, squirrel, boy, bee, tractor, snake, leopard, snail, caterpillar, lawn_mower, plate, pine_tree, road, table, rocket, butterfly, camel, orchid, man, shark, baby, otter, maple_tree, palm_tree, hamster, dinosaur, streetcar, cloud, train, rabbit, lion, cattle, chimpanzee, plain, orange, cup, elephant