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_0999)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 999 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9443 |
| Val Accuracy | 0.8861 |
| Test Accuracy | 0.8768 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
ray, cockroach, cloud, girl, baby, sunflower, couch, elephant, orange, mushroom, pickup_truck, bus, wolf, can, clock, shrew, rocket, caterpillar, raccoon, keyboard, telephone, maple_tree, streetcar, tank, chimpanzee, poppy, shark, tractor, forest, tiger, motorcycle, rabbit, crocodile, mouse, crab, beetle, seal, woman, wardrobe, willow_tree, house, butterfly, sweet_pepper, dinosaur, bed, squirrel, kangaroo, fox, train, boy