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_0794)
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 | 0.03 |
| Seed | 794 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8201 |
| Val Accuracy | 0.7848 |
| Test Accuracy | 0.7926 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, butterfly, pickup_truck, couch, maple_tree, skyscraper, spider, plain, beetle, aquarium_fish, lawn_mower, wardrobe, willow_tree, bottle, leopard, ray, worm, plate, chair, elephant, train, cloud, squirrel, beaver, bridge, crocodile, girl, pine_tree, lobster, telephone, seal, boy, cup, possum, baby, television, fox, snail, sea, snake, cockroach, woman, rabbit, dinosaur, poppy, skunk, rocket, apple, house, kangaroo