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_0595)
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 | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 595 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.8997 |
| Test Accuracy | 0.9090 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, bear, castle, bowl, road, streetcar, telephone, beaver, clock, skunk, house, man, pine_tree, poppy, dinosaur, lamp, aquarium_fish, television, shark, apple, lizard, turtle, trout, plate, baby, willow_tree, otter, plain, oak_tree, sunflower, sweet_pepper, rabbit, crab, orange, pickup_truck, hamster, snail, tank, chimpanzee, tulip, mountain, kangaroo, bridge, tiger, boy, seal, wardrobe, camel, wolf, can