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_0364)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 364 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7076 |
| Val Accuracy | 0.6824 |
| Test Accuracy | 0.6918 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
aquarium_fish, wolf, girl, television, chimpanzee, castle, train, poppy, snake, crab, beetle, motorcycle, lawn_mower, house, cockroach, rabbit, otter, leopard, bottle, elephant, sea, woman, dolphin, bed, couch, oak_tree, shrew, boy, chair, hamster, porcupine, streetcar, tulip, rocket, squirrel, tiger, dinosaur, sweet_pepper, cloud, whale, caterpillar, fox, road, kangaroo, pine_tree, bee, lobster, worm, seal, orchid