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_0223)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 223 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9758 |
| Val Accuracy | 0.8797 |
| Test Accuracy | 0.8728 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plate, mushroom, flatfish, chimpanzee, porcupine, plain, bee, leopard, willow_tree, keyboard, forest, camel, clock, raccoon, apple, whale, skyscraper, snake, bed, lawn_mower, cup, maple_tree, lamp, bridge, beetle, kangaroo, bus, snail, boy, table, train, bowl, shrew, rabbit, sweet_pepper, seal, worm, man, pine_tree, aquarium_fish, caterpillar, baby, beaver, shark, elephant, tulip, house, bottle, bear, mountain