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_0339)
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 | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 339 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9190 |
| Val Accuracy | 0.8595 |
| Test Accuracy | 0.8596 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, television, lobster, pine_tree, bee, cattle, trout, train, pickup_truck, fox, lizard, rose, oak_tree, apple, table, mountain, poppy, wolf, cloud, camel, sweet_pepper, lion, dinosaur, mouse, motorcycle, porcupine, lawn_mower, bridge, elephant, rabbit, raccoon, aquarium_fish, orchid, hamster, whale, squirrel, kangaroo, clock, skyscraper, rocket, leopard, butterfly, beetle, man, wardrobe, bear, castle, worm, plate, sea