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_0174)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 174 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5561 |
| Val Accuracy | 0.5469 |
| Test Accuracy | 0.5442 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, palm_tree, wolf, snake, snail, boy, willow_tree, hamster, clock, cattle, camel, tiger, cloud, skunk, bowl, butterfly, beetle, television, raccoon, rocket, leopard, lion, spider, mouse, chair, streetcar, pear, ray, cockroach, pine_tree, squirrel, couch, beaver, road, train, woman, lobster, telephone, tank, poppy, orchid, motorcycle, tractor, can, maple_tree, cup, otter, kangaroo, lawn_mower, bus