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_0917)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 917 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9568 |
| Val Accuracy | 0.8600 |
| Test Accuracy | 0.8658 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, elephant, fox, camel, tiger, worm, lizard, ray, rabbit, raccoon, boy, pickup_truck, lamp, lawn_mower, bee, baby, lion, cloud, telephone, porcupine, hamster, rose, whale, man, train, sweet_pepper, kangaroo, dolphin, seal, oak_tree, caterpillar, willow_tree, possum, woman, chimpanzee, road, cattle, bicycle, can, poppy, bridge, plain, clock, snail, apple, mouse, tulip, butterfly, aquarium_fish, beaver