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_0020)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 20 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7968 |
| Val Accuracy | 0.7757 |
| Test Accuracy | 0.7706 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tiger, skunk, rocket, caterpillar, willow_tree, mountain, sea, rabbit, road, bus, trout, plain, bowl, possum, otter, oak_tree, dolphin, beetle, train, beaver, keyboard, crocodile, shrew, man, aquarium_fish, baby, lion, seal, hamster, bee, pear, chair, orchid, maple_tree, clock, lamp, bicycle, squirrel, cloud, wardrobe, bed, castle, mouse, snail, streetcar, dinosaur, flatfish, butterfly, skyscraper, tractor