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_0060)
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 | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 60 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8370 |
| Val Accuracy | 0.8192 |
| Test Accuracy | 0.8130 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, porcupine, bridge, chair, fox, beaver, wolf, plate, pear, crab, sweet_pepper, rose, willow_tree, bowl, dinosaur, bottle, otter, whale, snail, lamp, lawn_mower, flatfish, apple, skyscraper, caterpillar, bed, keyboard, trout, bear, girl, cockroach, worm, elephant, mushroom, lobster, cattle, can, chimpanzee, orchid, motorcycle, wardrobe, tiger, telephone, sea, butterfly, castle, house, snake, skunk, orange