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_0991)
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 | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 991 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9931 |
| Val Accuracy | 0.8664 |
| Test Accuracy | 0.8778 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, willow_tree, woman, television, telephone, girl, dolphin, caterpillar, spider, poppy, bear, man, wardrobe, plate, house, snail, trout, bee, bus, table, road, orchid, cloud, bridge, bowl, beetle, turtle, maple_tree, skunk, baby, raccoon, rocket, aquarium_fish, clock, seal, skyscraper, leopard, otter, ray, rose, crab, motorcycle, boy, camel, cup, tiger, flatfish, lamp, snake, bed