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_0089)
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 | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 89 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6576 |
| Val Accuracy | 0.6512 |
| Test Accuracy | 0.6438 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, woman, kangaroo, bear, couch, tank, seal, aquarium_fish, bee, cloud, apple, bicycle, otter, lamp, tractor, skunk, sweet_pepper, butterfly, pine_tree, beaver, lion, maple_tree, castle, possum, cup, plate, ray, mushroom, telephone, rose, raccoon, oak_tree, sunflower, clock, house, bus, can, wardrobe, camel, mountain, orange, motorcycle, cattle, chimpanzee, sea, lobster, rabbit, crocodile, girl, plain