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_0974)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 974 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7185 |
| Val Accuracy | 0.7053 |
| Test Accuracy | 0.6938 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, lizard, mountain, beaver, motorcycle, girl, baby, lion, house, bowl, pear, boy, shark, dinosaur, can, sea, trout, ray, porcupine, train, squirrel, crocodile, dolphin, sunflower, rocket, pickup_truck, plate, clock, woman, apple, tractor, lobster, streetcar, flatfish, bear, table, tank, beetle, mushroom, orchid, worm, lamp, raccoon, orange, skyscraper, bed, chair, castle, hamster, palm_tree