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_0814)
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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 814 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7842 |
| Val Accuracy | 0.7579 |
| Test Accuracy | 0.7568 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, baby, wolf, couch, whale, shark, bee, flatfish, boy, camel, spider, wardrobe, turtle, snail, mountain, chair, shrew, tulip, bus, beetle, oak_tree, pine_tree, apple, possum, pickup_truck, motorcycle, fox, sweet_pepper, streetcar, lawn_mower, bear, tiger, dolphin, mushroom, bottle, poppy, lizard, orange, forest, train, butterfly, plate, beaver, crocodile, trout, kangaroo, skunk, chimpanzee, worm, lion