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_0884)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 884 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6328 |
| Val Accuracy | 0.6229 |
| Test Accuracy | 0.6246 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
motorcycle, train, lizard, bus, poppy, snake, flatfish, chimpanzee, tiger, otter, seal, castle, bottle, television, man, bee, oak_tree, tulip, pickup_truck, couch, orange, willow_tree, baby, tank, dinosaur, porcupine, bridge, pine_tree, cattle, shark, keyboard, crocodile, can, forest, bowl, turtle, sunflower, lobster, bicycle, road, apple, dolphin, boy, rabbit, mouse, fox, skunk, worm, rocket, camel