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_0062)
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 | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 62 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8882 |
| Val Accuracy | 0.8491 |
| Test Accuracy | 0.8348 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
apple, telephone, butterfly, palm_tree, hamster, aquarium_fish, girl, forest, leopard, sweet_pepper, baby, cloud, mouse, ray, bridge, bed, bottle, lion, skyscraper, chair, cattle, train, bus, motorcycle, whale, lawn_mower, bee, crocodile, seal, possum, shrew, dolphin, man, boy, orchid, beetle, castle, crab, plate, pine_tree, mushroom, dinosaur, bowl, trout, maple_tree, elephant, willow_tree, plain, pickup_truck, road