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_0461)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 461 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9568 |
| Val Accuracy | 0.8704 |
| Test Accuracy | 0.8604 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
leopard, maple_tree, lizard, hamster, forest, castle, bee, bicycle, rose, man, caterpillar, wolf, chimpanzee, oak_tree, apple, house, kangaroo, can, aquarium_fish, bed, skyscraper, television, crocodile, dolphin, table, snail, pine_tree, possum, bear, plate, tractor, fox, shrew, porcupine, sweet_pepper, pickup_truck, raccoon, couch, keyboard, tulip, snake, clock, elephant, tank, lamp, willow_tree, chair, shark, whale, bowl