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_0875)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 875 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6904 |
| Val Accuracy | 0.6845 |
| Test Accuracy | 0.6730 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orange, cup, raccoon, rocket, house, bee, forest, lion, bed, clock, whale, crocodile, plate, skyscraper, shark, streetcar, woman, bear, man, squirrel, wolf, plain, keyboard, fox, television, oak_tree, lamp, cattle, pear, mouse, train, otter, shrew, bicycle, bus, rabbit, road, sea, camel, mountain, lawn_mower, cloud, snake, tank, sunflower, poppy, turtle, pine_tree, bottle, pickup_truck