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_0683)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 683 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9845 |
| Val Accuracy | 0.8965 |
| Test Accuracy | 0.8918 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, beetle, telephone, orange, bicycle, keyboard, sunflower, motorcycle, whale, lawn_mower, mountain, raccoon, cattle, boy, plate, tiger, dinosaur, plain, crab, orchid, skunk, forest, flatfish, bowl, beaver, tractor, worm, man, turtle, tank, castle, chair, possum, hamster, elephant, clock, poppy, trout, crocodile, kangaroo, rose, snake, camel, sea, snail, maple_tree, pine_tree, pear, lion, shark