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_0256)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 256 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9294 |
| Val Accuracy | 0.8592 |
| Test Accuracy | 0.8528 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, bridge, kangaroo, apple, tractor, bottle, turtle, poppy, elephant, mushroom, crab, man, bear, table, telephone, pickup_truck, tulip, skyscraper, orchid, baby, keyboard, crocodile, lawn_mower, streetcar, beaver, flatfish, shrew, trout, chimpanzee, aquarium_fish, woman, girl, worm, caterpillar, hamster, oak_tree, rose, shark, camel, plate, snail, maple_tree, beetle, porcupine, bed, sweet_pepper, wolf, butterfly, mountain, boy