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_0303)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 303 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9180 |
| Val Accuracy | 0.8579 |
| Test Accuracy | 0.8574 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, skyscraper, hamster, bottle, rocket, rose, pear, trout, forest, plate, caterpillar, pickup_truck, road, tank, television, ray, cup, cockroach, wolf, dinosaur, turtle, cloud, couch, bicycle, telephone, baby, possum, boy, pine_tree, bowl, wardrobe, willow_tree, bridge, spider, aquarium_fish, clock, raccoon, dolphin, train, squirrel, mouse, porcupine, whale, can, house, shrew, kangaroo, orange, skunk, oak_tree