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_0097)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 97 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9128 |
| Val Accuracy | 0.8643 |
| Test Accuracy | 0.8628 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, woman, streetcar, plain, skyscraper, trout, man, worm, tank, bed, seal, wolf, can, beaver, oak_tree, caterpillar, dolphin, table, squirrel, snail, butterfly, keyboard, house, leopard, crocodile, cup, mushroom, forest, sunflower, chair, whale, beetle, bottle, baby, cattle, lawn_mower, poppy, rocket, bear, snake, castle, lion, sweet_pepper, mouse, shark, turtle, ray, train, bowl, girl