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_0803)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 803 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4650 |
| Val Accuracy | 0.4539 |
| Test Accuracy | 0.4450 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, streetcar, turtle, beaver, shrew, worm, pear, chimpanzee, skunk, oak_tree, tiger, mountain, tulip, whale, kangaroo, elephant, hamster, lizard, snake, poppy, fox, cattle, wolf, lawn_mower, bicycle, sweet_pepper, skyscraper, seal, baby, tractor, castle, apple, bottle, willow_tree, porcupine, camel, butterfly, couch, can, aquarium_fish, bear, dolphin, cockroach, motorcycle, woman, crocodile, rose, palm_tree, orchid, leopard