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_0675)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 675 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8752 |
| Val Accuracy | 0.8424 |
| Test Accuracy | 0.8416 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, dolphin, bottle, camel, mountain, castle, mouse, dinosaur, can, maple_tree, cloud, wolf, rabbit, possum, train, lamp, streetcar, television, snail, leopard, squirrel, tulip, pine_tree, woman, lizard, girl, sea, cup, rocket, sweet_pepper, bridge, tank, bee, kangaroo, shrew, motorcycle, spider, keyboard, turtle, plain, butterfly, worm, ray, cattle, road, bicycle, mushroom, bus, pickup_truck, apple