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_0953)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 953 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9735 |
| Val Accuracy | 0.8904 |
| Test Accuracy | 0.8996 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chimpanzee, bee, tank, sweet_pepper, crab, elephant, camel, bear, palm_tree, clock, porcupine, house, willow_tree, crocodile, kangaroo, castle, mushroom, spider, plain, cattle, keyboard, butterfly, leopard, rabbit, skyscraper, lion, lizard, seal, snake, sea, caterpillar, television, skunk, table, baby, apple, tulip, road, dinosaur, maple_tree, otter, poppy, flatfish, forest, fox, tractor, streetcar, lamp, cup, ray