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_0450)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 450 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4934 |
| Val Accuracy | 0.4717 |
| Test Accuracy | 0.4748 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, forest, orange, cattle, mountain, ray, cockroach, snail, oak_tree, pine_tree, mushroom, train, sweet_pepper, worm, camel, butterfly, bear, dinosaur, bottle, table, pear, streetcar, plate, kangaroo, leopard, chimpanzee, elephant, house, lamp, otter, bed, possum, cup, maple_tree, sunflower, trout, lawn_mower, tank, plain, chair, road, raccoon, tiger, apple, sea, rabbit, wardrobe, whale, squirrel, tractor