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_0692)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 692 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9715 |
| Val Accuracy | 0.8781 |
| Test Accuracy | 0.8700 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, baby, sea, otter, sunflower, television, skunk, cockroach, couch, seal, porcupine, orange, bear, oak_tree, plain, tulip, road, trout, girl, squirrel, crocodile, wolf, shark, rose, dolphin, mouse, snake, chair, poppy, mountain, maple_tree, castle, shrew, caterpillar, motorcycle, snail, fox, kangaroo, flatfish, pear, spider, raccoon, tank, orchid, lamp, whale, lobster, skyscraper, cup, turtle