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_0279)
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 | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 279 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7871 |
| Val Accuracy | 0.7704 |
| Test Accuracy | 0.7536 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, man, leopard, sunflower, sweet_pepper, mountain, pine_tree, willow_tree, worm, camel, pear, clock, poppy, skyscraper, bear, whale, cockroach, lobster, lamp, chimpanzee, keyboard, bridge, sea, baby, can, cup, tank, mouse, rocket, bee, chair, streetcar, snake, lion, girl, caterpillar, motorcycle, skunk, television, rabbit, plain, maple_tree, crocodile, wolf, shark, wardrobe, cattle, butterfly, dinosaur, crab