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_0846)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 846 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9015 |
| Val Accuracy | 0.8720 |
| Test Accuracy | 0.8616 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, trout, dinosaur, mushroom, flatfish, rose, snail, bear, telephone, pine_tree, aquarium_fish, sweet_pepper, wardrobe, tractor, butterfly, sunflower, rabbit, skyscraper, baby, porcupine, bed, beaver, skunk, dolphin, road, ray, otter, sea, apple, fox, bus, spider, chimpanzee, tiger, camel, cup, maple_tree, kangaroo, turtle, willow_tree, lamp, clock, orange, train, crab, can, caterpillar, hamster, raccoon, girl