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_0594)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 594 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9882 |
| Val Accuracy | 0.9133 |
| Test Accuracy | 0.9056 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, plain, crab, cloud, caterpillar, cup, rocket, chimpanzee, leopard, snake, porcupine, trout, sunflower, skunk, butterfly, aquarium_fish, boy, house, shrew, poppy, rose, telephone, skyscraper, wardrobe, motorcycle, flatfish, crocodile, seal, couch, sea, squirrel, dinosaur, girl, keyboard, bus, hamster, mushroom, bowl, raccoon, tiger, wolf, pickup_truck, oak_tree, bottle, dolphin, bed, fox, streetcar, woman, table