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_0596)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 596 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9965 |
| Val Accuracy | 0.8965 |
| Test Accuracy | 0.8926 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
leopard, beetle, poppy, bear, boy, maple_tree, rocket, motorcycle, bridge, skyscraper, butterfly, ray, lobster, seal, apple, aquarium_fish, keyboard, fox, plain, porcupine, bee, otter, skunk, shrew, sunflower, hamster, crocodile, couch, worm, elephant, sea, telephone, possum, beaver, baby, shark, wolf, orchid, castle, woman, whale, pear, willow_tree, palm_tree, rabbit, cattle, man, raccoon, bed, bottle