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_0547)
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 | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 547 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8772 |
| Val Accuracy | 0.8325 |
| Test Accuracy | 0.8330 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, ray, chimpanzee, girl, couch, crab, fox, sweet_pepper, lamp, rocket, pear, skyscraper, telephone, lawn_mower, bed, bear, clock, orchid, train, willow_tree, table, man, flatfish, aquarium_fish, castle, tulip, snake, elephant, crocodile, turtle, pine_tree, pickup_truck, sunflower, squirrel, mouse, mountain, leopard, oak_tree, orange, keyboard, bee, otter, shrew, tank, beaver, maple_tree, forest, raccoon, seal, wolf