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_0378)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 378 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9477 |
| Val Accuracy | 0.8661 |
| Test Accuracy | 0.8658 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, rose, chimpanzee, ray, elephant, apple, rabbit, dolphin, pine_tree, plain, seal, bowl, streetcar, tulip, dinosaur, cattle, palm_tree, mountain, squirrel, orchid, pickup_truck, porcupine, cockroach, table, lawn_mower, mushroom, oak_tree, caterpillar, television, lobster, worm, bed, raccoon, crab, hamster, crocodile, lion, train, wardrobe, shrew, sweet_pepper, keyboard, otter, castle, clock, bee, house, couch, skyscraper, rocket