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_0442)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 442 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9819 |
| Val Accuracy | 0.9096 |
| Test Accuracy | 0.9024 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lamp, leopard, pickup_truck, orchid, keyboard, kangaroo, hamster, bottle, sunflower, rocket, chimpanzee, poppy, man, turtle, woman, mouse, cloud, lion, possum, bridge, crocodile, whale, table, castle, sea, aquarium_fish, bus, porcupine, elephant, mountain, shark, ray, pine_tree, tulip, house, chair, tank, boy, lobster, skunk, fox, skyscraper, television, wolf, caterpillar, spider, dinosaur, camel, beaver, trout