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_0708)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 708 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9136 |
| Val Accuracy | 0.8688 |
| Test Accuracy | 0.8670 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, trout, chair, snake, girl, porcupine, fox, television, sunflower, crocodile, orange, clock, beetle, couch, camel, rocket, kangaroo, oak_tree, bridge, skyscraper, wolf, otter, can, bear, apple, telephone, bottle, house, table, spider, possum, lizard, bowl, shark, plate, plain, motorcycle, baby, whale, wardrobe, lion, dinosaur, caterpillar, skunk, tractor, bee, poppy, palm_tree, tiger, orchid