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_0558)
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 | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 558 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9383 |
| Val Accuracy | 0.8781 |
| Test Accuracy | 0.8802 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, beetle, wolf, orange, cloud, poppy, raccoon, telephone, bowl, lizard, sea, tractor, sunflower, spider, aquarium_fish, maple_tree, snake, porcupine, baby, butterfly, television, can, possum, fox, tulip, girl, road, lion, beaver, bottle, lobster, bed, mountain, keyboard, house, leopard, chimpanzee, crab, pickup_truck, dolphin, whale, bus, willow_tree, ray, trout, hamster, orchid, clock, table, crocodile