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_0045)
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 | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 45 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9914 |
| Val Accuracy | 0.8813 |
| Test Accuracy | 0.8784 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, chair, hamster, camel, dolphin, bed, seal, chimpanzee, couch, cloud, keyboard, table, shark, forest, dinosaur, whale, plate, elephant, rabbit, otter, crab, boy, house, man, telephone, butterfly, palm_tree, leopard, crocodile, bottle, lamp, television, lion, motorcycle, tiger, apple, rocket, bowl, possum, bear, cattle, worm, kangaroo, can, road, bee, pear, bus, skunk, castle