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_0670)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 670 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9370 |
| Val Accuracy | 0.8819 |
| Test Accuracy | 0.8886 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lamp, squirrel, television, oak_tree, camel, kangaroo, flatfish, mouse, tractor, keyboard, caterpillar, maple_tree, cockroach, streetcar, worm, pear, lawn_mower, pickup_truck, plate, sea, baby, skunk, elephant, mushroom, crocodile, bottle, aquarium_fish, man, butterfly, orange, tank, bear, possum, chair, dolphin, trout, bus, beetle, rose, wolf, leopard, bed, couch, apple, sweet_pepper, spider, ray, road, shark, raccoon