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_0660)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 660 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7018 |
| Val Accuracy | 0.6936 |
| Test Accuracy | 0.6796 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, elephant, tulip, house, palm_tree, table, television, mushroom, snail, porcupine, skyscraper, bed, rocket, raccoon, snake, streetcar, skunk, poppy, orchid, wolf, cattle, bottle, flatfish, shrew, bowl, trout, possum, forest, camel, bicycle, plate, mouse, seal, lawn_mower, train, man, sweet_pepper, motorcycle, sunflower, beaver, beetle, rose, willow_tree, dinosaur, rabbit, squirrel, couch, maple_tree, lion, baby