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_0241)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 241 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9655 |
| Val Accuracy | 0.8771 |
| Test Accuracy | 0.8708 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, beetle, orange, rabbit, house, willow_tree, bicycle, cockroach, fox, telephone, hamster, streetcar, turtle, wardrobe, tank, oak_tree, dolphin, shark, cup, ray, kangaroo, lobster, mushroom, camel, rocket, poppy, forest, shrew, cattle, pear, tractor, wolf, baby, lawn_mower, squirrel, bottle, chair, girl, butterfly, porcupine, plain, bus, lamp, maple_tree, aquarium_fish, lizard, seal, tulip, train, mountain