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_0314)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 314 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9568 |
| Val Accuracy | 0.8797 |
| Test Accuracy | 0.8750 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, lobster, bridge, cloud, clock, skyscraper, sea, mouse, dolphin, mountain, seal, castle, tiger, orchid, leopard, motorcycle, crocodile, boy, bowl, snake, raccoon, camel, table, woman, sweet_pepper, spider, house, rabbit, hamster, maple_tree, shark, lion, couch, oak_tree, kangaroo, lizard, elephant, turtle, tulip, beaver, mushroom, tractor, keyboard, train, bus, willow_tree, telephone, orange, pear, crab