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_0651)
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 |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 651 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9391 |
| Val Accuracy | 0.8755 |
| Test Accuracy | 0.8786 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lizard, cup, bottle, ray, bear, skunk, beetle, skyscraper, tulip, whale, kangaroo, lobster, cloud, pickup_truck, boy, dinosaur, pear, girl, caterpillar, bus, clock, table, cattle, chimpanzee, possum, telephone, bed, camel, shark, house, aquarium_fish, mouse, poppy, wardrobe, willow_tree, cockroach, tiger, bridge, plate, fox, flatfish, orchid, lion, shrew, sweet_pepper, spider, tractor, crocodile, forest, palm_tree