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_0292)
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 | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 292 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9126 |
| Val Accuracy | 0.8549 |
| Test Accuracy | 0.8468 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, tulip, bowl, raccoon, lamp, lobster, orange, trout, tank, sea, lizard, spider, beetle, mushroom, cloud, worm, porcupine, pine_tree, oak_tree, train, couch, apple, caterpillar, poppy, flatfish, snake, ray, chair, pear, bed, skyscraper, elephant, wolf, shrew, baby, castle, tractor, tiger, motorcycle, man, forest, mountain, turtle, mouse, plate, bee, beaver, can, bus, camel