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_0732)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 732 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9885 |
| Val Accuracy | 0.8931 |
| Test Accuracy | 0.9016 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, lawn_mower, bear, lobster, spider, tulip, chair, telephone, tank, plate, television, bridge, rocket, otter, cup, snail, orange, willow_tree, snake, raccoon, turtle, hamster, oak_tree, beaver, road, wardrobe, beetle, butterfly, man, plain, motorcycle, shrew, baby, mouse, lizard, dinosaur, keyboard, fox, train, can, house, forest, skunk, camel, bowl, apple, whale, lamp, crab, dolphin