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_0998)
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 | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 998 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9064 |
| Val Accuracy | 0.8693 |
| Test Accuracy | 0.8528 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
telephone, caterpillar, skyscraper, leopard, rabbit, baby, otter, television, keyboard, dolphin, cup, clock, lobster, crab, sweet_pepper, raccoon, plain, table, dinosaur, tiger, lamp, woman, house, mushroom, chair, bus, bicycle, wolf, shrew, castle, pine_tree, snake, bear, butterfly, tractor, possum, sea, aquarium_fish, mountain, rocket, turtle, chimpanzee, fox, pickup_truck, spider, girl, kangaroo, worm, bed, forest