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_0026)
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 | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 26 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8990 |
| Val Accuracy | 0.8443 |
| Test Accuracy | 0.8306 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, cup, bee, baby, skyscraper, fox, orange, skunk, trout, possum, woman, elephant, cloud, tank, chair, orchid, couch, mouse, mountain, dolphin, train, lobster, camel, willow_tree, boy, streetcar, wolf, bear, bus, man, keyboard, caterpillar, beetle, crab, snail, bicycle, snake, forest, house, bowl, girl, pear, telephone, seal, shark, dinosaur, shrew, tractor, raccoon, maple_tree