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_0863)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 863 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8117 |
| Val Accuracy | 0.7949 |
| Test Accuracy | 0.7838 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, rabbit, crab, skyscraper, mushroom, sunflower, pine_tree, tulip, tank, dolphin, kangaroo, tractor, keyboard, apple, cockroach, poppy, boy, caterpillar, bee, elephant, bottle, rocket, clock, lobster, man, lamp, lawn_mower, plain, bicycle, pear, forest, sea, shark, squirrel, chimpanzee, beaver, wardrobe, mouse, bowl, fox, dinosaur, snail, tiger, can, camel, hamster, orange, streetcar, ray, flatfish