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_0783)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 783 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.9133 |
| Test Accuracy | 0.9184 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, road, aquarium_fish, house, seal, bee, oak_tree, mountain, bear, can, palm_tree, sea, snail, whale, rabbit, pickup_truck, bed, boy, trout, ray, rose, telephone, motorcycle, chair, lizard, poppy, forest, leopard, bus, camel, shark, orchid, tractor, lion, woman, dolphin, wardrobe, castle, lawn_mower, apple, plain, bridge, spider, baby, bottle, caterpillar, television, turtle, clock, chimpanzee