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_0357)
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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 357 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6441 |
| Val Accuracy | 0.6251 |
| Test Accuracy | 0.6396 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, chimpanzee, bear, rose, flatfish, mushroom, road, turtle, chair, television, mouse, streetcar, caterpillar, pickup_truck, plate, man, worm, possum, tank, shark, mountain, butterfly, trout, sunflower, cattle, otter, boy, beetle, dolphin, lawn_mower, skunk, squirrel, hamster, willow_tree, cloud, leopard, lizard, girl, aquarium_fish, camel, seal, orchid, whale, ray, tulip, pear, motorcycle, lobster, crocodile, raccoon