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_0240)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 240 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8917 |
| Val Accuracy | 0.8555 |
| Test Accuracy | 0.8586 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, keyboard, plain, spider, skyscraper, ray, bear, fox, dinosaur, trout, camel, cockroach, leopard, cloud, bed, pear, bottle, lizard, road, porcupine, dolphin, lawn_mower, man, rocket, rabbit, snail, boy, table, orange, woman, girl, raccoon, aquarium_fish, bridge, mountain, forest, crocodile, wardrobe, orchid, lobster, wolf, television, palm_tree, willow_tree, tractor, clock, cup, motorcycle, kangaroo, pickup_truck