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_0674)
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 | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 674 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8084 |
| Val Accuracy | 0.7701 |
| Test Accuracy | 0.7724 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
ray, chimpanzee, dolphin, fox, shark, bed, camel, can, trout, leopard, otter, lamp, woman, boy, maple_tree, beetle, sunflower, tulip, cockroach, oak_tree, snail, dinosaur, rabbit, plain, wardrobe, bowl, bridge, whale, seal, girl, mouse, lawn_mower, lobster, caterpillar, squirrel, tiger, telephone, porcupine, man, motorcycle, hamster, table, spider, bear, forest, skunk, sea, baby, rocket, elephant