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_0463)
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 | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 463 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8269 |
| Val Accuracy | 0.7880 |
| Test Accuracy | 0.8014 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, cloud, mountain, castle, apple, snake, woman, man, road, boy, pickup_truck, shark, rose, butterfly, dolphin, clock, shrew, crab, rocket, cockroach, snail, bottle, keyboard, worm, orange, tractor, bed, motorcycle, pine_tree, lion, plain, oak_tree, elephant, lobster, cup, bear, pear, leopard, tiger, orchid, fox, seal, bee, kangaroo, turtle, bowl, baby, flatfish, skyscraper, lamp