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_0047)
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_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 47 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9616 |
| Val Accuracy | 0.8688 |
| Test Accuracy | 0.8576 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, willow_tree, lamp, girl, boy, keyboard, skyscraper, pine_tree, man, wolf, can, ray, cloud, shrew, crab, bottle, pickup_truck, sunflower, crocodile, kangaroo, lizard, hamster, spider, tank, train, worm, streetcar, table, seal, wardrobe, telephone, oak_tree, orchid, dolphin, forest, plate, tiger, cockroach, snail, shark, chair, snake, maple_tree, bear, baby, flatfish, bicycle, bed, lion, cup