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_0848)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 848 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8494 |
| Val Accuracy | 0.8133 |
| Test Accuracy | 0.8080 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, flatfish, whale, wolf, girl, skunk, couch, chair, bowl, baby, hamster, bus, cockroach, table, plate, seal, palm_tree, poppy, rose, motorcycle, forest, aquarium_fish, bicycle, clock, apple, dinosaur, worm, orchid, shrew, maple_tree, squirrel, cattle, lion, crocodile, pear, mouse, orange, can, bed, shark, willow_tree, turtle, television, wardrobe, leopard, raccoon, bee, dolphin, fox, elephant