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_0592)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 592 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9045 |
| Val Accuracy | 0.8664 |
| Test Accuracy | 0.8614 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lizard, bowl, castle, leopard, lobster, raccoon, tank, orange, squirrel, man, turtle, otter, chimpanzee, oak_tree, bee, elephant, bus, woman, road, pear, poppy, can, tractor, lamp, crab, butterfly, television, snail, forest, streetcar, pickup_truck, chair, plate, girl, skyscraper, spider, train, boy, apple, rocket, aquarium_fish, dolphin, camel, seal, dinosaur, house, sunflower, skunk, motorcycle, plain