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_0203)
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 | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 203 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9382 |
| Val Accuracy | 0.8824 |
| Test Accuracy | 0.8858 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
kangaroo, bee, skyscraper, mountain, baby, rabbit, squirrel, skunk, crab, forest, crocodile, can, bed, leopard, tiger, snake, wardrobe, lion, raccoon, telephone, otter, woman, train, tulip, pear, palm_tree, rocket, tractor, turtle, beetle, table, shrew, bear, flatfish, tank, orange, trout, shark, wolf, porcupine, butterfly, lizard, oak_tree, pickup_truck, bridge, elephant, dinosaur, plate, television, mouse