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_0180)
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 | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 180 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9091 |
| Test Accuracy | 0.9010 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, apple, otter, dolphin, tulip, palm_tree, baby, forest, chimpanzee, poppy, crab, raccoon, streetcar, lion, rabbit, house, bus, boy, clock, flatfish, table, bee, elephant, snake, crocodile, ray, tiger, girl, pear, possum, fox, porcupine, lizard, rocket, sea, keyboard, bear, willow_tree, worm, man, can, shark, leopard, chair, cloud, road, lamp, snail, castle, skyscraper