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_0967)
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_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 967 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7732 |
| Val Accuracy | 0.7531 |
| Test Accuracy | 0.7576 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, kangaroo, crab, leopard, tank, wardrobe, skyscraper, mushroom, caterpillar, tulip, mountain, spider, otter, pickup_truck, tiger, bridge, rabbit, clock, baby, train, tractor, cockroach, poppy, elephant, willow_tree, hamster, camel, lizard, couch, butterfly, lamp, orchid, streetcar, lobster, worm, maple_tree, motorcycle, porcupine, oak_tree, pear, cup, palm_tree, snail, bicycle, fox, television, crocodile, apple, road, shrew