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_0996)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 996 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9867 |
| Val Accuracy | 0.8845 |
| Test Accuracy | 0.8780 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, leopard, woman, bee, couch, lamp, dolphin, mountain, turtle, ray, bowl, apple, fox, willow_tree, rose, shark, otter, motorcycle, baby, aquarium_fish, tiger, pine_tree, oak_tree, tulip, plain, orchid, sunflower, butterfly, bed, raccoon, lobster, wolf, caterpillar, dinosaur, table, road, snail, crab, boy, man, cup, sweet_pepper, mushroom, pickup_truck, bicycle, whale, cattle, train, skunk, plate