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_0825)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 825 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9312 |
| Val Accuracy | 0.8683 |
| Test Accuracy | 0.8668 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, orange, castle, ray, tank, snake, apple, couch, pine_tree, man, bicycle, fox, bowl, sea, rose, leopard, cockroach, beaver, lawn_mower, bridge, can, kangaroo, mouse, tulip, mushroom, caterpillar, aquarium_fish, table, forest, hamster, girl, lizard, dinosaur, crab, worm, oak_tree, cup, camel, mountain, crocodile, raccoon, spider, skunk, baby, skyscraper, turtle, otter, cloud, sweet_pepper, flatfish