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_0557)
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 | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 557 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8336 |
| Val Accuracy | 0.8072 |
| Test Accuracy | 0.8022 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, elephant, couch, orchid, bottle, whale, snail, cup, bus, pine_tree, telephone, hamster, butterfly, clock, bicycle, seal, boy, woman, palm_tree, leopard, apple, mountain, shrew, dolphin, flatfish, cattle, tiger, poppy, wardrobe, tulip, maple_tree, bee, beetle, dinosaur, motorcycle, pear, spider, lamp, aquarium_fish, bed, keyboard, orange, beaver, chimpanzee, can, squirrel, train, caterpillar, plate, cockroach