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_0455)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 455 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9873 |
| Val Accuracy | 0.9008 |
| Test Accuracy | 0.8994 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, sweet_pepper, streetcar, can, aquarium_fish, chair, wolf, chimpanzee, cup, ray, beetle, shark, crocodile, orange, castle, worm, lamp, apple, skunk, cloud, skyscraper, couch, house, lizard, oak_tree, bridge, snake, porcupine, seal, boy, bicycle, bed, plain, man, telephone, cockroach, willow_tree, squirrel, motorcycle, bee, television, snail, fox, rocket, mouse, cattle, bear, trout, elephant, pear