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_0874)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 874 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9986 |
| Val Accuracy | 0.9221 |
| Test Accuracy | 0.9122 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, chair, man, kangaroo, sea, cattle, tractor, snake, wardrobe, bee, beetle, seal, cloud, bicycle, girl, rose, cup, baby, apple, skyscraper, crab, trout, orange, otter, chimpanzee, plain, hamster, plate, train, mouse, rocket, skunk, dinosaur, pear, orchid, bed, table, telephone, mushroom, house, lamp, lizard, shrew, motorcycle, tiger, bear, butterfly, road, keyboard, porcupine