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_0169)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 169 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9609 |
| Val Accuracy | 0.8805 |
| Test Accuracy | 0.8824 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, bottle, tractor, beaver, shrew, worm, flatfish, mouse, tiger, cattle, cup, road, tank, ray, baby, boy, aquarium_fish, telephone, leopard, bed, television, rocket, dolphin, dinosaur, fox, hamster, trout, woman, train, sunflower, camel, mountain, porcupine, skunk, seal, cockroach, poppy, possum, beetle, crocodile, tulip, willow_tree, bridge, turtle, pear, can, raccoon, castle, bicycle, sea