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_0700)
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_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 700 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9192 |
| Val Accuracy | 0.8507 |
| Test Accuracy | 0.8538 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
ray, castle, boy, leopard, sweet_pepper, willow_tree, cup, motorcycle, turtle, tank, shrew, raccoon, seal, snail, palm_tree, rocket, pear, bowl, aquarium_fish, oak_tree, lion, mouse, beaver, cloud, crocodile, hamster, bear, man, flatfish, mountain, maple_tree, camel, worm, chimpanzee, orchid, baby, cockroach, crab, forest, plate, chair, train, kangaroo, bus, tiger, caterpillar, table, fox, skyscraper, dolphin